[go: up one dir, main page]

Das et al., 2015 - Google Patents

Cross-lingual transfer learning during supervised training in low resource scenarios.

Das et al., 2015

View PDF
Document ID
9604726936908242286
Author
Das A
Hasegawa-Johnson M
Publication year
Publication venue
INTERSPEECH

External Links

Snippet

In this study, transfer learning techniques are presented for cross-lingual speech recognition to mitigate the effects of limited availability of data in a target language using data from richly resourced source languages. A maximum likelihood (ML) based regularization criterion is …
Continue reading at www.isca-archive.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/14—Speech classification or search using statistical models, e.g. hidden Markov models [HMMs]
    • G10L15/142—Hidden Markov Models [HMMs]
    • G10L15/144—Training of HMMs
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
    • G10L15/187—Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/065—Adaptation
    • G10L15/07—Adaptation to the speaker
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
    • G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
    • G10L15/197—Probabilistic grammars, e.g. word n-grams
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/16—Speech classification or search using artificial neural networks
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L2015/088—Word spotting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6267—Classification techniques
    • G06K9/6268—Classification techniques relating to the classification paradigm, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6217—Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/005—Language recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/68—Methods or arrangements for recognition using electronic means using sequential comparisons of the image signals with a plurality of references in which the sequence of the image signals or the references is relevant, e.g. addressable memory
    • G06K9/6807—Dividing the references in groups prior to recognition, the recognition taking place in steps; Selecting relevant dictionaries
    • G06K9/6842—Dividing the references in groups prior to recognition, the recognition taking place in steps; Selecting relevant dictionaries according to the linguistic properties, e.g. English, German
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems

Similar Documents

Publication Publication Date Title
Das et al. Cross-lingual transfer learning during supervised training in low resource scenarios.
Swietojanski et al. Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR
Qawaqneh et al. Deep neural network framework and transformed MFCCs for speaker's age and gender classification
Chen et al. Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition
Seltzer et al. Multi-task learning in deep neural networks for improved phoneme recognition
Miao et al. EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding
Huang et al. Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers
Ghoshal et al. Multilingual training of deep neural networks
Kanda et al. Elastic spectral distortion for low resource speech recognition with deep neural networks
Siniscalchi et al. Experiments on cross-language attribute detection and phone recognition with minimal target-specific training data
Lee et al. Mispronunciation detection via dynamic time warping on deep belief network-based posteriorgrams
Bell et al. Multi-level adaptive networks in tandem and hybrid ASR systems
CN107851434A (en) Speech recognition system and method using adaptive incremental learning method
Mohan et al. Multi-lingual speech recognition with low-rank multi-task deep neural networks
Siniscalchi et al. Speech recognition using long-span temporal patterns in a deep network model
Yu et al. Deep neural network-hidden markov model hybrid systems
Tüske et al. Multilingual hierarchical MRASTA features for ASR.
Razavi et al. On modeling context-dependent clustered states: Comparing HMM/GMM, hybrid HMM/ANN and KL-HMM approaches
Lu et al. Cross-lingual subspace gaussian mixture models for low-resource speech recognition
Liu et al. Adapting ASR for under-resourced languages using mismatched transcriptions
Lee et al. The 2015 nist language recognition evaluation: the shared view of i2r, fantastic4 and singams
Rizwan et al. A weighted accent classification using multiple words
Huang et al. Feature space maximum a posteriori linear regression for adaptation of deep neural networks.
Tomashenko et al. Evaluation of feature-space speaker adaptation for end-to-end acoustic models
Tomashenko et al. On the Use of Gaussian Mixture Model Framework to Improve Speaker Adaptation of Deep Neural Network Acoustic Models.