Notes:
Speech recognizers are software systems that are used to convert spoken language into written text. Speech recognizers use advanced algorithms and machine learning techniques to analyze the sound waves of spoken language and to identify the words and sentences being spoken. This allows speech recognizers to transcribe spoken language into written text, which can be used for a variety of purposes, such as dictation, transcription, or language translation.
In the context of dialog systems, speech recognizers are used to process and interpret the spoken input of users. Dialog systems typically include a speech recognition component, which is responsible for converting the user’s spoken input into written text. This written text is then passed to other components of the dialog system, such as natural language understanding or text generation, which are responsible for generating a response to the user’s input.
See also:
Speech Recognition Meta Guide | Speech Synthesis Meta Guide
Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition
H Soltau, H Liao, H Sak – arXiv preprint arXiv:1610.09975, 2016 – arxiv.org
We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly using deep bi-directional LSTM …
Using out-of-language data to improve an under-resourced speech recognizer
D Imseng, P Motlicek, H Bourlard, PN Garner – Speech communication, 2014 – Elsevier
Under-resourced speech recognizers may benefit from data in languages other than the target language. In this paper, we report how to boost the performance of an Afrikaans automatic speech recognition system by using already available Dutch data. We …
Artificial neural networks as speech recognisers for dysarthric speech: Identifying the best-performing set of MFCC parameters and studying a speaker-independent …
SR Shahamiri, SSB Salim – Advanced Engineering Informatics, 2014 – Elsevier
Dysarthria is a neurological impairment of controlling the motor speech articulators that compromises the speech signal. Automatic Speech Recognition (ASR) can be very helpful for speakers with dysarthria because the disabled persons are often physically …
14.4 A scalable speech recognizer with deep-neural-network acoustic models and voice-activated power gating
M Price, J Glass… – Solid-State Circuits …, 2017 – ieeexplore.ieee.org
The applications of speech interfaces, commonly used for search and personal assistants, are diversifying to include wearables, appliances, and robots. Hardware-accelerated automatic speech recognition (ASR) is needed for scenarios that are constrained by power …
Free on-line speech recogniser based on Kaldi ASR toolkit producing word posterior lattices
O Plátek, F Jur?í?ek – Proceedings of the 15th Annual Meeting of the …, 2014 – aclweb.org
This paper presents an extension of the Kaldi automatic speech recognition toolkit to support on-line recognition. The resulting recogniser supports acoustic models trained using state-of-theart acoustic modelling techniques. As the recogniser produces word posterior lattices, it is …
Spoken term detection using phoneme transition network from multiple speech recognizers’ outputs
S Natori, Y Furuya, H Nishizaki… – Journal of Information …, 2013 – jstage.jst.go.jp
?? Spoken Term Detection (STD) that considers the out-of-vocabulary (OOV) problem has generated significant interest in the field of spoken document processing. This study describes STD with false detection control using phoneme transition networks (PTNs) …
Learning L2 pronunciation with a mobile speech recognizer: French/y/.
D Liakin, W Cardoso, N Liakina – CALICO Journal, 2015 – search.ebscohost.com
This study investigates the acquisition of the L2 French vowel/y/in a mobileassisted learning environment, via the use of automatic speech recognition (ASR). Particularly, it addresses the question of whether ASR-based pronunciation instruction using a mobile device can …
A 6 mW, 5, 000-Word Real-Time Speech Recognizer Using WFST Models.
M Price, JR Glass, AP Chandrakasan – J. Solid-State Circuits, 2015 – ieeexplore.ieee.org
We describe an IC that provides a local speech recog-nition capability for a variety of electronic devices. We start with a generic speech decoder architecture that is programmable with industry-standard WFST and GMM speech models. Algorithm and …
Improving multiple-crowd-sourced transcriptions using a speech recogniser
RC van Dalen, KM Knill, P Tsiakoulis… – Acoustics, Speech and …, 2015 – core.ac.uk
This paper introduces a method to produce high-quality transcriptions of speech data from only two crowd-sourced transcriptions. These transcriptions, produced cheaply by people on the Internet, for example through Amazon Mechanical Turk, are often of low quality. Often …
Cluster-based dynamic variance adaptation for interconnecting speech enhancement pre-processor and speech recognizer
M Delcroix, S Watanabe, T Nakatani… – Computer Speech & …, 2013 – Elsevier
A conventional approach to noise robust speech recognition consists of employing a speech enhancement pre-processor prior to recognition. However, such a pre-processor usually introduces artifacts that limit recognition performance improvement. In this paper we discuss …
A Hindi speech recognizer for an agricultural video search application
K Bali, S Sitaram, S Cuendet, I Medhi – … of the 3rd ACM Symposium on …, 2013 – dl.acm.org
Voice user interfaces for ICTD applications have immense potential in their ability to reach to a large illiterate or semi-literate population in these regions where text-based interfaces are of little use. However, building speech systems for a new language is a highly resource …
Estimating room acoustic parameters for speech recognizer adaptation and combination in reverberant environments
F Xiong, S Goetze, BT Meyer – Acoustics, Speech and Signal …, 2014 – ieeexplore.ieee.org
This work analyzes the influence of reverberation on automatic speech recognition (ASR) systems and how to compensate its influence, with special focus on the important acoustical parameters ie room reverberation time T 60 and clarity index C 50. A multilayer perceptron …
Comparative analysis of adapted foreign language and native Lithuanian speech recognizers for voice user interface
V Rudzionis, G Raskinis, R Maskeliunas… – Elektronika ir …, 2013 – eejournal.ktu.lt
Paper presents research results obtained when building a speaker independent hybrid speech recognizer. This recognizer will be integrated as a phrase recognizer in a medical-pharmaceutical information system. The hybrid speech recognizer consists of two …
A 6mW 5k-word real-time speech recognizer using WFST models
M Price, J Glass… – Solid-State Circuits …, 2014 – ieeexplore.ieee.org
Hardware-accelerated speech recognition is needed to supplement today’s cloud-based systems in power-and bandwidth-constrained scenarios such as wearable electronics. With efficient hardware speech decoders, client devices can seamlessly transition between cloud …
Intelligibility assessment and speech recognizer word accuracy rate prediction for dysarthric speakers in a factor analysis subspace
D Martínez, E Lleida, P Green, H Christensen… – ACM Transactions on …, 2015 – dl.acm.org
Automated intelligibility assessments can support speech and language therapists in determining the type of dysarthria presented by their clients. Such assessments can also help predict how well a person with dysarthria might cope with a voice interface to assistive …
A German distant speech recognizer based on 3D beamforming and harmonic missing data mask
JA Morales-Cordovilla, H Pessentheiner… – AIA-DAGA, 2013 – researchgate.net
This paper addresses the problem of distant speech recognition in reverberant noise conditions applying a star-shaped microphone array and missing data techniques. The performance of the system is evaluated over a German database, which has been …
Evaluation of methods to combine different speech recognizers
T Rasymas, V Rudžionis – Computer Science and Information …, 2015 – ieeexplore.ieee.org
The paper deals with the problem of improving speech recognition by combining outputs of several different recognizers. We are presenting our results obtained by experimenting with different classification methods which are suitable to combine outputs of different speech …
Formalizing expert knowledge for developing accurate speech recognizers.
A Kumar, F Metze, W Wang, M Kam – INTERSPEECH, 2013 – isca-speech.org
The expertise required to develop a speech recognition system with reasonable accuracy for a given task is quite significant, and precludes most non-speech experts from integrating speech recognition into their own research. While an initial baseline recognizer may readily …
Syllable based continuous speech recognizer with varied length maximum likelihood character segmentation
AA Ganesh, C Ravichandran – Advances in Computing …, 2013 – ieeexplore.ieee.org
Speech is the most natural and quick mode of transforming and sharing information. To automate the process of speech production and perception, many researches are carried out for more than five decades. For an Automatic speech Recognition (ASR) of a large or …
Improving speech recognizer using neuro-genetic weights connection strategy for spoken query information retrieval
N Seman, ZA Bakar, N Jamil – Asia Information Retrieval Symposium, 2013 – Springer
This paper describes the integration of speech recognizer into information retrieval (IR) system to retrieve text documents relevant to the given spoken queries. Our aim is to improve the speech recognizer since it has been proven as crucial for the front end of a …
A garbage model generation technique for embedded speech recognisers
M Alessandrini, G Biagetti, A Curzi… – … and Applications (SPA …, 2013 – ieeexplore.ieee.org
In this paper we present a simple but effective technique to help the designer of a voice-operated appliance add out-of-grammar command rejection capabilities, with a minimal effort and without overly degrading the recognition accuracy. Given the desired operational …
Feature extraction and dimensionality reduction using IPS for isolated tamil words speech recognizer
KM Krishna, MV Lakshmi… – International Journal of …, 2014 – pdfs.semanticscholar.org
Automatic Speech Recognition (ASR), is the process of converting a speech waveform into the text quite similar to the information being communicated by the speaker. This paper aims to construct a speech recognition system for Tamil language. Mel Frequency Cepstral …
Integration of an on-line Kaldi speech recogniser to the Alex dialogue systems framework
O Plátek, F Jur?í?ek – International Conference on Text, Speech, and …, 2014 – Springer
This paper describes the integration of an on-line Kaldi speech recogniser into the Alex Dialogue Systems Framework (ADSF). As the Kaldi OnlineLatgenRecogniser is written in C++, we first developed a Python wrapper for the recogniser so that the ADSF, written in …
Compensation of recording position shifts for a myoelectric silent speech recognizer
M Wand, C Schulte, M Janke… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org
A myoelectric Silent Speech Recognizer is a system which recognizes speech by capturing the electrical activity of the human articulatory muscles, thus enabling the user to communicate silently. We recently devised a recording setup based on electrode arrays with …
Linking cognitive tokens to biological signals: Dialogue context improves neural speech recognizer performance
R Veale, G Briggs, M Scheutz – Proceedings of the …, 2013 – cloudfront.escholarship.org
This paper presents a hybrid cognitive model engaged in experiments demonstrating a successful mechanism for applying top-down contextual bias to a neural speech recognition system to improve its performance. The hybrid model includes a model of social dialogue …
A cross-lingual adaptation approach for rapid development of speech recognizers for learning disabled users
M Bohac, M Kucharova, Z Callejas, J Nouza… – EURASIP Journal on …, 2014 – Springer
Building a voice-operated system for learning disabled users is a difficult task that requires a considerable amount of time and effort. Due to the wide spectrum of disabilities and their different related phonopathies, most approaches available are targeted to a specific …
A new approach to develop a syllable based, continuous amharic speech recognizer
YB Gebremedhin, F Duckhorn… – EUROCON, 2013 …, 2013 – ieeexplore.ieee.org
All of the previous syllable based Automatic Speech Recognizers (ASRs) for the Amharic language are built by training a separate acoustic model for each of the 196 distinctly pronounced Consonant-Vowel (CV) syllable. In this paper, we will demonstrate that a …
Tamil Speech Recognizer Using Hidden Markov Model for Question Answering System of Railways
G Vignesh, SS Ganesh – Artificial Intelligence and Evolutionary Algorithms …, 2015 – Springer
The research on speech and natural language is in progress for more than two decades. Recently, researchers are focused on developing speech interfaces to their corresponding automated system. For voice-based question answering system, there is the need for …
Speaking rate normalization with lattice-based context-dependent phoneme duration modeling for personalized speech recognizers on mobile devices.
CF Yeh, H Lee, LS Lee – INTERSPEECH, 2013 – isca-speech.org
Voice access of cloud applications including social networks using mobile devices becomes attractive today. And personalized speech recognizers over mobile devices become feasible because most mobile devices have only a single user. Speaking rate variation is known to …
A metric for evaluating speech recognizer output based on human-perception model
N Itoh, G Kurata, R Tachibana… – … Annual Conference of …, 2015 – isca-speech.org
Abstract 1 Word error rate or character error rate are usually used as the metrics for evaluating the accuracy of speech recognition. These are naturally-defined objective metrics and are helpful for comparing recognition methods fairly. However the overall performance …
Read My Lips: Towards Use of the Microsoft Kinect as a Visual-Only Automatic Speech Recognizer
P McKay, B Clement, S Haverty, E Newton… – Ninth Symposium On …, 2013 – Citeseer
Consumer devices used in the home are capable of collecting ever more information from users, including audio and video. The Microsoft Kinect is particularly well-designed for tracking user speech and motion. In this paper, we explore the ability of current models of …
Unicode Sinhala and phonetic English bi-directional conversion for Sinhala speech recognizer
M Punchimudiyanse… – Industrial and Information …, 2015 – ieeexplore.ieee.org
An automated speech recognizer (ASR) having a large vocabulary is yet to be developed for the Sinhala language because of the time consumed in gathering the training data to build a language model. The dictionary and building the language model require non-English text …
Automatic continuous speech recogniser for Dravidian languages using the auto associative neural network
J Sangeetha, S Jothilakshmi – International Journal of …, 2016 – inderscienceonline.com
In recent times with the extensive improvement of computers, numerous methods of data interchange between man and computer are revealed. It aims to provide an efficient way for human to communicate with computers exclusively for people with disabilities who face …
A hybrid noise suppression filter for accuracy enhancement of commercial speech recognizers in varying noisy conditions
KY Chan, PC Yong, S Nordholm, CKF Yiu… – Applied soft computing, 2014 – Elsevier
Commercial speech recognizers have made possible many speech control applications such as wheelchair, tone-phone, multifunctional robotic arms and remote controls, for the disabled and paraplegic. However, they have a limitation in common in that recognition …
Demystifying development of speech recognizers for novices
A Kumar, F Metze, E Riebling, M Kam – Proc. Designing Speech and …, 2014 – cs.cmu.edu
Despite recent popularity of interfaces such as Google Now or Siri, speech-enabled systems are not yet developed in abundance to support every type of user group, language, or acoustic scenario. A core issue is the difficulty involved in building a “reasonably accurate” …
Bottleneck linear transformation network adaptation for speaker adaptive training-based hybrid DNN-HMM speech recognizer
T Ochiai, S Matsuda, H Watanabe, X Lu… – … , Speech and Signal …, 2016 – ieeexplore.ieee.org
Recently, a Hybrid DNN-HMM recognizer trained with the Speaker Adaptive Training (SAT) concept was successfully modified to a more effective speaker-adaptation-oriented recognizer whose DNN front-end adopted a Linear Transformation Network (LTN) Speaker …
On the Use of Automatic Speech Recognizers for the Quality and Intelligibility Prediction of Synthetic Speech
F Hinterleitner, S Zander, KP Engelbrecht… – Proc. Elektron …, 2015 – Citeseer
In this paper we investigate the use of an automatic speech recognizer (Google Speech API) for the prediction of quality and intelligibility of synthetic speech. For two databases of rated synthetic speech samples, we analyze the correlation of the word error rates (WER) …
Analysis-by-synthesis frame dropping algorithm together with a novel speech recognizer using time-varying hidden Markov model
LM Lee, FR Jean – Systems, Man and Cybernetics (SMC), 2014 …, 2014 – ieeexplore.ieee.org
In distributed speech recognition applications, variable frame rate (VFR) analysis is a technique that can reduce the channel bandwidth and computation resources. In this method, slowly changing frames that provide little information are abandoned. Rapidly …
TAMEEM V1. 0: speakers and text independent Arabic automatic continuous speech recognizer
MAM Abushariah – International Journal of Speech Technology, 2017 – Springer
This research work aims to disseminate the efforts towards developing and evaluating TAMEEM V1. 0, which is a state-of-the-art pure Modern Standard Arabic (MSA), automatic, continuous, speaker independent, and text independent speech recognizer using high …
Towards an end-to-end speech recognizer for Portuguese using deep neural networks
IM Quintanilha, LWP Biscainho, SL Netto – XXXV Simpósio Brasileiro de …, 2017 – sbrt.org.br
This paper presents an open-source character-based end-to-end speech recognition system for Brazilian Portuguese (PT-BR). The first step of the work was the development of a PT-BR dataset—an ensemble of 4 previous datasets (of which 3 publicly available). The model …
Automatic speech recognizers for Mexican Spanish and its open resources
CD Hernández-Mena, IV Meza-Ruiz… – Journal of Applied …, 2017 – Elsevier
Abstract Development of automatic speech recognition systems relies on the availability of distinct language resources such as speech recordings, pronunciation dictionaries, and language models. These resources are scarce for the Mexican Spanish dialect. In this work …
UNFOLD: a memory-efficient speech recognizer using on-the-fly WFST composition
R Yazdani, JM Arnau, A González – … of the 50th Annual IEEE/ACM …, 2017 – dl.acm.org
Abstract Accurate, real-time Automatic Speech Recognition (ASR) requires huge memory storage and computational power. The main bottleneck in state-of-the-art ASR systems is the Viterbi search on a Weighted Finite State Transducer (WFST). The WFST is a graph-based …
This thesis is about eh… Finding the optimal combination of filled pauses to improve a keyword spotting automatic speech recogniser.
B Verbart – 2015 – theses.ubn.ru.nl
This study aims to improve a keyword spotting (KWS) automatic speech recogniser (ASR) system by adding different combinations of filled pauses to its keyword list. The research questions the study revolves around are:“How do filled pauses manifest themselves in …
Acoustic Driving Simulator Design for Evaluating an In-car Speech Recognizer
S Lee, S Kang – Phonetics and Speech Sciences, 2013 – koreascience.or.kr
This paper is on designing an indoor driving simulator to evaluate the performance of in-car speech recognizer when influenced by the elements, which lower the success rate of speech recognition. The proposed simulator simulates vehicle noise which was pre …
Speech enhancement in vehicular environments as a front end for robust speech recogniser
DSK Lena, P Vijayalakshmi – Intelligent Computing and Control …, 2017 – ieeexplore.ieee.org
The term “Speech Enhancement” refers to improving quality and intelligibility of the degraded speech. The current work focuses on three speech enhancement techniques.(1) Speech enhancement based subspace modelling using EVD (Eigen value …
Continuous Sinhala Speech Recognizer
HND Thilini – 2013 – documents.ucsc.lk
Speech is the most natural way of communication among humans. Speech recognition is the process of transforming a speech signal into its corresponding word sequence. When the recognition is carried out by a computer program, it is known as Automatic Speech …
A Low-Power Speech Recognizer and Voice Activity Detector Using Deep Neural Networks
M Price, J Glass… – IEEE Journal of Solid-State …, 2018 – ieeexplore.ieee.org
This paper describes digital circuit architectures for automatic speech recognition (ASR) and voice activity detection (VAD) with improved accuracy, programmability, and scalability. Our ASR architecture is designed to minimize off-chip memory bandwidth, which is the main …
Improving Multiple-Crowd-Sourced Transcriptions Using a Speech Recogniser
KM Knill, P Tsiakoulis, MJ Gales – 2015 – repository.cam.ac.uk
This paper introduces a method to produce high-quality transcriptions of speech data from only two crowd-sourced transcriptions. These transcriptions, produced cheaply by people on the Internet, for example through Amazon Mechanical Turk, are often of low quality. Often …
Prediction Of Consonants Intelligibility For Listeners With Normal Hearing Using Microscopic Models Of Speech Perception Considering Different Distance Measures In Automatic Speech Recognizer
M GERAVANCHIZADEH, ALI FALLAH… – 2015 – en.journals.sid.ir
In this study, recognition rates of consonants available in vowel-consonant-vowel structure in hearing tests and two microscopic models will be investigated. Such a syllable structure doesn’t exist in Farsi and Azerbaijani languages, but since the goal is only recognition of …
Robust Parallel Speech Recognition: Robust Speech Recognition of Noisy or Reverberated Data Using Multiple Recognizers in Different Energy Bands
A Maier – 2015 – dl.acm.org
… This is beneficial if noise only occurs in parts of the spectrum. In this manner multiple speech recognizers are trained which analyze disjoint parts of the frequency domain. Each of the speech recognizers extracts a different word chain from the audio signal …
Impact of each camera on multiple camera visual speech recognizer using ANOVA: A brief study
A Biswas, PK Sahu, M Chandra – TENCON 2015-2015 IEEE …, 2015 – ieeexplore.ieee.org
Multiple camera fusion technique is an imperative part of multi-camera computer vision applications. Visual modality plays a vital role in computer vision systems when the acoustic modality is corrupted by the background noise. Multiple camera protocol allows the user to …
A Combined Rough Sets–K-means Vector Quantization Model for Arabic Speech Recognizer
EA Mohamed, H Adlan, AR Ramli – pdfs.semanticscholar.org
Vector quantization (VQ), is considered an efficient data reduction technique, and is used as a preprocessing stage in speech recognition systems. Methods traditionally used for vector quantization are purely numerical methods rather than rule-based methods. Furthermore …
The Study on Automatic Speech Recognizer Utilizing Mobile Platform on Korean EFL Learners’ Pronunciation Development
AY Park – ?????????? ???, 2017 – dbpia.co.kr
Combining different speech recognizers by using CART classifier
T Rasymas, V Rudžionis – … AIEEE), 2015 IEEE 3rd Workshop on …, 2015 – ieeexplore.ieee.org
This paper presents out results obtained by experimenting with CART classifier which may be used for creating hybrid speech recognition system. We tried to create speech recognition system which is capable of producing more than 95% accuracy by recognizing …
Building HMM Independent Isolated Speech Recognizer System for Amazigh Language
S El Ouahabi, M Atounti, M Bellouki – Europe and MENA Cooperation …, 2017 – Springer
This paper describes the implementation of Hidden Markov Model based speaker independent spoken digits and letters speech recognition system for Amazigh language which is an official language in Morocco. The system is developed using HTK. The system is …
Speech Recognizer Adaptation: Recognizer Adaptation by Acoustic Model Interpolation
A Maier – 2015 – dl.acm.org
This book focuses on the adaptation of speech recognizers to noisy or reverberant environment. Therefore, three corpora in different noise and reverberation levels are presented. Speech recognition is used. Basics are omitted. As features Mel Frequency …
A fully-hardwired implementation of large vocabulary continuous speech recognizer
Y Kim, J Kim, J Lee, W Kim – Consumer Electronics (ISCE) …, 2015 – ieeexplore.ieee.org
This article presents the hardware implementation of the speech recognition for real time performance and high-level accuracy. The stand-alone speech recognizer should simultaneously achieve the requirements, which are the low-latency performance and the …
Utilizing multiple speech recognizers to improve spoken language understanding performance
SJ Choi, K Lee, M Hahn – Consumer Electronics (ISCE 2014) …, 2014 – ieeexplore.ieee.org
This paper proposes the method of enhancing the spoken language understanding performance by employing general domain and domain specific speech recognizer. Apply intent to the result from general domain and domain specifically trained speech recognizer …
Improving Speech Recognizers by Refining Broadcast Data with Inaccurate Subtitle Timestamps
JU Bang, MY Choi, SH Kim… – Proc. Interspeech …, 2017 – pdfs.semanticscholar.org
This paper proposes an automatic method to refine broadcast data collected every week for efficient acoustic model training. For training acoustic models, we use only audio signals, subtitle texts, and subtitle timestamps accompanied by recorded broadcast programs …
Development of Bengali Automatic Speech Recognizer and Analysis of Error Pattern
FN Choudhury, TM Shamma, U Rafiq, HR Shuvo – researchgate.net
Abstract—The very first step for ASR was taken in 1932 and still this speech recognizing technology is constantly evolving. Although Bengali is one of the largest spoken languages in the world, a few works on Bengali speech recognition has been found in different literature reviews. There …
Robust Feature Extraction for Bimodal Speech Recognizer
ETH TIK – 2013 – Citeseer
The following progress report on the Vision-Supported Speech-Based Human Machine Interaction (VSHMI) project provides the summary of the activity to date on the project and the remaining steps needed to be accomplished from the Speech Processing Group’s point …
An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech
H Seki, S Watanabe, T Hori, J Le Roux, JR Hershey – 2018 – merl.com
End-to-end automatic speech recognition (ASR) can significantly reduce the burden of developing ASR systems for new languages, by eliminating the need for linguistic information such as pronunciation dictionaries. This also creates an opportunity to build a …
Enhancing HMM Based Malayalam Continuous Speech Recognizer Using Artificial Neural Networks
A Mohamed, KNR Nair – … Intelligence in Data Mining-Volume 2, 2015 – Springer
Improving discrimination in recognition systems is a subject of research in recent years. Neural network classifiers are naturally discriminative and can be easily applied to real-world problems. This paper examines the use of multilayer perceptrons as the emission …
Online Library Management Using Voice Recognizer Robot System
KS Kumar – academia.edu
This project aims to develop an efficient robot using a laser pointer for a library management system. The gestures of the robot are designed by its body movements. The robot is predesigned with the estimation results of human behavior and is capable of receiving the …
Design & Development Of Discrete Hmm (Dhmm) Isolated Hindi Speech Recognizer
S Kumar, J Prakash – JOURNAL OF INDIAN …, 2014 – mujournal.mewaruniversity.in
This paper describes the insight of the design & development of a Proposed Hindi Speech Recognizer based on the discrete hidden Markov model (DHMM). Here we have proposed a new Quantizer which has been used with discrete hidden Markov modeling to get a …
Speech recognizer for regional languages of Pakistan
SA Ali, B Ashraf, HA Owais… – Robotics and Emerging …, 2014 – ieeexplore.ieee.org
This paper introduces the speech recognizer developed in the regional languages of Pakistan: Urdu, Punjabi, Sindhi and Pashto for performing three different supervised operations (Turn on/Turn off Door, Turn on/Turn off Light, Turn on/Turn off Fan) on real time …
Integration Of A Kaldi Speech Recognizer Into A Speech Dialog System For Automotive Infotainment Applications
T Ranzenberger, C Hacker, F Gallwitz, N Germany – essv2018.de
In this paper we present an evaluation of the Kaldi speech recognizer in an automotive context. We integrate Kaldi into an existing software tool which is used to specify human-machine interfaces including speech dialogs for automotive and non-automotive domains …
Development Of Front End And Statistical Model For A Hindi Speech Recognizer: A Practical Approach
S Kumar, J Prakash – JOURNAL OF INDIAN …, 2014 – mujournal.mewaruniversity.in
This paper describes the different approaches for the development of front end and statistical model for Hindi Speech Recognizer. The front end includes the preprocessing of speech signal such as capturing of raw speech signal, its digitization and converting it into …
Personalized Speech Recognizer with Keyword-Based Personalized Lexicon and Language Model Using Word Vector Representations
CF Yeh, Y Liou, H Lee, L Lee – Sixteenth Annual Conference of the …, 2015 – isca-speech.org
The popularity of mobile devices offers an ideal platform for personalized recognizers. With data collected from the user, the personalized recognizer with better matched acoustic and linguistic characteristics can offer not only better recognition accuracy but also less …
Continuous speech recognizer for low-end embedded devices
A Milinkovi?, S Milinkovi? – Embedded Computing (MECO) …, 2015 – ieeexplore.ieee.org
This paper discusses the implementation of continuous speech recognition system for low-cost bare-metal platform. The applied algorithms are well known, however they are optimized for constrained embedded environment. System is very flexible since it uses …
Enhanced Spoken Sentence Retrieval Using a Conventional Automatic Speech Recognizer in Smart Home
H Ahn, H Kim – International Journal on Artificial Intelligence Tools, 2016 – World Scientific
With the rapid evolution of smart home environment, the demand for spoken information retrieval (eg, voice-activated FAQ retrieval) on information appliances is increasing. In spoken information retrieval, users’ spoken queries are converted into text queries using …
A Noise-Robust Speech Recogniser supported by a TMS320C31 Platform
P Gómez, A Alvarez, R Marttnez, M Pérez, V Rodellar… – junipera.datsi.fi.upm.es
Robust Speech Recognition Techniques are necessary in many applications where the environment is too noisy to obtain reliable recognition rates with standard Speech Recognisers. This is especially so in Car Cabinets, Avionics, Military Vehicles …
Automatic Generation of Proper Noun Entries in a Speech Recognizer for Local Information Recognition
K Shiga, T Nose, A Ito, R Masumura, H Masataki – 2016 – researchgate.net
In this paper, we developed a method to generate proper nouns that would actually be uttered by users of speech recognizer when inputting local information. The generated proper nouns are added to the dictionary of speech recognizer to improve recognition …
A Low Power Tone Recognition for Automatic Tonal Speech Recognizer
J Chaiwongsai, W Chiracharit… – … on Fundamentals of …, 2013 – search.ieice.org
This paper proposes a low power tone recognition suitable for automatic tonal speech recognizer (ATSR). The tone recognition estimates fundamental frequency (F 0) only from vowels by using a new magnitude difference function (MDF), called vowel-MDF …
Experiments on front-end techniques and segmentation model for robust Indian Language speech recognizer
R Sriranjani, BM Karthick… – … (NCC), 2014 Twentieth …, 2014 – ieeexplore.ieee.org
Recent contributions in the area of Automatic Speech Recognition (ASR) for Indian Languages has been increased. This paper serves as a comprehensive study of different feature extraction methods namely MFCC, PLP, RASTA-PLP and PNCC. An attempt to find …
Towards a Speech Recognizer for Multiple Languages Using Arabic Acoustic Model Application to Amazigh Language
A Sadiqui, A Zinedine – International Conference on Arabic Language …, 2017 – Springer
The construction of acoustic models of a language, used in automatic speech recognition (ASR) systems, is a developed technology achievable without great difficulty when a large amount of speech and written corpus is available. However, these technological resources …
Improving the Accuracy of Large Vocabulary Continuous Speech Recognizer Using Dependency Parse Tree and Chomsky Hierarchy in Lattice Rescoring
KS Hong, TP Tan, EK Tang – Asian Language Processing …, 2013 – ieeexplore.ieee.org
This research work describes our approaches in using dependency parse tree information to derive useful hidden word statistics to improve the baseline system of Malay large vocabulary automatic speech recognition system. The traditional approaches to train …
Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers
T Ochiai, S Matsuda, H Watanabe, X Lu… – … on Information and …, 2016 – search.ieice.org
Among various training concepts for speaker adaptation, Speaker Adaptive Training (SAT) has been successfully applied to a standard Hidden Markov Model (HMM) speech recognizer, whose state is associated with Gaussian Mixture Models (GMMs). On the other …
Design & Development Of Continuous Density Hmm (Cdhmm) Isolated Hindi Speech Recognizer
S Kumar, J Prakash – Development, 2015 – ijaerd.co.in
This paper describes the insight of the design & development of a Proposed Hindi Speech Recognizer based on the continuous density hidden Markov model (CDHMM). Here we have proposed a new recognizer which have been used with continuous density hidden …