NDLI: HMM-based speech segmentation: improvements of fully automatic approaches

Content Provider	ACM Digital Library
Author	Brognaux, Sandrine Drugman, Thomas
Copyright Year	2016
Abstract	Speech segmentation refers to the problem of determining the phoneme boundaries from an acoustic recording of an utterance together with its orthographic transcription. This paper focuses on a particular case of hidden Markov model (HMM)-based forced alignment in which the models are directly trained on the corpus to align. The obvious advantage of this technique is that it is applicable to any language or speaking style and does not require manually aligned data. Through a systematic step-by-step study, the role played by various training parameters (e.g. models configuration, number of training iterations) on the alignment accuracy is assessed, with corpora varying in speaking style and language. Based on a detailed analysis of the errors commonly made by this technique, we also investigate the use of additional fully automatic strategies to improve the alignment. Beside the use of supplementary acoustic features, we explore two novel approaches: an initialization of the silence models based on a voice activity detection (VAD) algorithm and the consideration of the forced alignment of the time-reversed sound. The evaluation is carried out on 12 corpora of different sizes, languages (some being under-resourced) and speaking styles. It aims at providing a comprehensive study of the alignment accuracy achieved by the different versions of the speech segmentation algorithm depending on corpus-related specificities. While the baseline method is shown to reach good alignment rates with corpora as small as 2 minutes, we also emphasize the benefit of using a few seconds of bootstrapping data. Regarding improvement methods, our results show that the insertion of additional features outperforms both other strategies. The performance of VAD, however, is shown to be notably striking on very small corpora, correcting more than 60% of the errors superior to 40 ms. Finally, the combination of the three improvement methods is also pointed out as providing the highest alignment rates, with very low variability across the corpora, regardless of their size. This combined technique is shown to outperform available speaker-independent models, improving the alignment rate by 8 to 10% absolute.
Starting Page	5
Ending Page	15
Page Count	11
File Format	PDF
ISSN	23299290
e-ISSN	23299304
DOI	10.1109/TASLP.2015.2456421
Volume Number	24
Issue Number	1
Journal	IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-01-01
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Corpora annotation Hidden markov models Phonetic alignment Speech segmentation
Content Type	Text
Resource Type	Article
Subject	Instrumentation Computational Mathematics Signal Processing Electrical and Electronic Engineering Acoustics and Ultrasonics Speech and Hearing Media Technology

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

HMM-Based Speech Segmentation: Improvements of Fully Automatic Approaches

Turbo automatic speech recognition

Train&align: A new online tool for automatic phonetic alignment

Characterizing Phonetic Transformations and Acoustic Differences Across English Dialects

A Deep Generative Architecture for Postfiltering in Statistical Parametric Speech Synthesis

Temporally Varying Weight Regression: A Semi-Parametric Trajectory Model for Automatic Speech Recognition

Unsegmented Dialogue Act Annotation and Decoding With N-Gram Transducers

Automatic Speech Recognition for Mixed Dialect Utterances by Mixing Dialect Language Models

A New HMM-Based Voice Conversion Methodology Evaluated on Monolingual and Cross-Lingual Conversion Tasks

HMM-based speech segmentation: improvements of fully automatic approaches

Similar Documents

HMM-Based Speech Segmentation: Improvements of Fully Automatic Approaches

Turbo automatic speech recognition

Train&align: A new online tool for automatic phonetic alignment

Characterizing Phonetic Transformations and Acoustic Differences Across English Dialects

A Deep Generative Architecture for Postfiltering in Statistical Parametric Speech Synthesis

Temporally Varying Weight Regression: A Semi-Parametric Trajectory Model for Automatic Speech Recognition

Unsegmented Dialogue Act Annotation and Decoding With N-Gram Transducers

Automatic Speech Recognition for Mixed Dialect Utterances by Mixing Dialect Language Models

A New HMM-Based Voice Conversion Methodology Evaluated on Monolingual and Cross-Lingual Conversion Tasks

HMM-based speech segmentation: improvements of fully automatic approaches