1 |
A comparative study of several parameterizations for speaker recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Speaker verification in mismatch training and testing conditions ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
A New Amharic Speech Emotion Dataset and Classification Benchmark ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Subspace-based Representation and Learning for Phonotactic Spoken Language Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
LPC Augment: An LPC-Based ASR Data Augmentation Algorithm for Low and Zero-Resource Children's Dialects ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Automatic Dialect Density Estimation for African American English ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system ...
|
|
|
|
Abstract:
End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse performance on utterances containing infrequent proper nouns. In this work, we propose to add a contextual bias attention (CBA) module to attention based encoder decoder (AED) model to improve its ability of recognizing the contextual phrases. Specifically, CBA utilizes the context vector of source attention in decoder to attend to a specific bias embedding. Jointly learned with the basic AED parameters, CBA can tell the model when and where to bias its output probability distribution. At inference stage, a list of bias phrases is preloaded and we adapt the posterior distributions of both CTC and attention decoder according to the attended bias phrase of CBA. We evaluate the proposed method on GigaSpeech and achieve a consistent relative improvement on recall rate of bias ... : 5 pages, 5 tabels, 1 figure ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Sound cs.SD
|
|
URL: https://arxiv.org/abs/2202.09003 https://dx.doi.org/10.48550/arxiv.2202.09003
|
|
BASE
|
|
Hide details
|
|
11 |
Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
SHAS: Approaching optimal Segmentation for End-to-End Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Automatic Detection of Speech Sound Disorder in Child Speech Using Posterior-based Speaker Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Telepractice treatment of rhotics (Peterson et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Telepractice treatment of rhotics (Peterson et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Towards a Perceptual Model for Estimating the Quality of Visual Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Learning and controlling the source-filter representation of speech with a variational autoencoder ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Correcting Misproducted Speech using Spectrogram Inpainting ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Decoding Neural Correlation of Language-Specific Imagined Speech using EEG Signals ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|