Far-Field End-to-End Text-Dependent Speaker Verification Based on Mixed Training Data with Transfer Learning and Enrollment Data Augmentation

Qin, Xiaoyi; Cai, Danwei; Li, Ming

doi:10.21437/interspeech.2019-1542

Cited by 30 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the experiments in [22], the strategy of transfer learning performs well in the far-field text-dependent speaker verification tasks. Therefore, we select the data from SLR38, SLR47 [23], SLR62, SLR82 [24], SLR85 [25] on openslr 5…”

Section: Speaker Verification Network Architecturementioning

confidence: 99%

The 2020 Personalized Voice Trigger Challenge: Open Datasets, Evaluation Metrics, Baseline System and Results

Jia¹,

Wang²,

Qin

et al. 2021

Interspeech 2021

Self Cite

View full text Add to dashboard Cite

The 2020 Personalized Voice Trigger Challenge (PVTC2020) addresses two different research problems a unified setup: joint wake-up word detection with speaker verification on close-talking single microphone data and far-field multi-channel microphone array data. Specially, the second task poses an additional cross-channel matching challenge on top of the far-field condition. To simulate the real-life application scenario, the enrollment utterances are recorded from close-talking cell-phone only, while the test utterances are recorded from both the close-talking cell-phone and the far-field microphone arrays. This paper introduces our challenge setup and the released database as well as the evaluation metrics. In addition, we present a joint end-to-end neural network baseline system trained with the proposed database for speaker-dependent wake-up word detection. Results show that the cost calculated from the miss rate and the false alarm rate, can reach 0.37 in the close-talking single microphone task and 0.31 in the far-field microphone array task. The official website 1 and the open-source baseline system have been released. 2

show abstract

Section: Speaker Verification Network Architecturementioning

confidence: 99%

The 2020 Personalized Voice Trigger Challenge: Open Datasets, Evaluation Metrics, Baseline System and Results

Jia¹,

Wang²,

Qin

et al. 2021

Interspeech 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…HI-MIA includes two sub databases, which are the AISHELLwakeup 1 with utterances from 254 speakers and the AISHELL-2019B-eval dataset with utterances from 86 speakers. 23 The AISHELL-wakeup database has 3,936,003 utterances with 1,561.12 hours in total. The content of utterances covers two wake-up words, 'ni hao, mi ya ("你好，米雅")' in chinese and 'Hi, Mia' in English.…”

Section: The Hi-mia Databasementioning

confidence: 99%

HI-MIA: A Far-Field Text-Dependent Speaker Verification Database and the Baselines

Qin

Bu²,

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

This paper presents a far-field text-dependent speaker verification database named HI-MIA. We aim to meet the data requirement for far-field microphone array based speaker verification since most of the publicly available databases are single channel close-talking and text-independent. The database contains recordings of 340 people in rooms designed for the far-field scenario. Recordings are captured by multiple microphone arrays located in different directions and distance to the speaker and a high-fidelity close-talking microphone. Besides, we propose a set of end-to-end neural network based baseline systems that adopt single-channel data for training. Moreover, we propose a testing background aware enrollment augmentation strategy to further enhance the performance. Results show that the fusion systems could achieve 3.29% EER in the far-field enrollment far field testing task and 4.02% EER in the close-talking enrollment and far-field testing task.

show abstract

“…In practice, to achieve the state-of-the-art performance, text-dependent SV requires the same set of text to be spoken during the training stage and the test stage. [9,10,11]. When there is no or limited training data with the designated phrase to build a text-dependent SV system, those data augmentation approaches couldn't help to get promising performance.…”

Section: Introductionmentioning

confidence: 99%

Unit Selection Synthesis Based Data Augmentation for Fixed Phrase Speaker Verification

Huang

Xiang²,

Zhao³

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Data augmentation is commonly used to help build a robust speaker verification system, especially in limited-resource case. However, conventional data augmentation methods usually focus on the diversity of acoustic environment, leaving the lexicon variation neglected. For text dependent speaker verification tasks, it's well-known that preparing training data with the target transcript is the most effectual approach to build a well-performing system, however collecting such data is time-consuming and expensive. In this work, we propose a unit selection synthesis based data augmentation method to leverage the abundant text-independent data resources. In this approach text-independent speeches of each speaker are firstly broke up to speech segments each contains one phone unit. Then segments that contain phonetics in the target transcript are selected to produce a speech with the target transcript by concatenating them in turn. Experiments are carried out on the AISHELL Speaker Verification Challenge 2019 database, the results and analysis shows that our proposed method can boost the system performance significantly.

show abstract

Far-Field End-to-End Text-Dependent Speaker Verification Based on Mixed Training Data with Transfer Learning and Enrollment Data Augmentation

Cited by 30 publications

References 33 publications

The 2020 Personalized Voice Trigger Challenge: Open Datasets, Evaluation Metrics, Baseline System and Results

The 2020 Personalized Voice Trigger Challenge: Open Datasets, Evaluation Metrics, Baseline System and Results

HI-MIA: A Far-Field Text-Dependent Speaker Verification Database and the Baselines

Unit Selection Synthesis Based Data Augmentation for Fixed Phrase Speaker Verification

Contact Info

Product

Resources

About