Hao Tang 唐顥
Papers
Phonetic analysis of self-supervised representations of english speech Dan Wells , Hao Tang, Korin Richmond
Speech audio corrector: using speech from non-target speakers for one-off correction of mispronunciations in grapheme-input text-to-speech Gustav Eje Henter , Hao Tang, Simon King
Autoregressive Co-Training for Learning Discrete Speech Representation Sung-Ling Yeh , Hao Tang
Hierarchical sketch induction for paraphrase generation Tom Hosking , Hao Tang, Mirella Lapata
Supervised attention in sequence-to-sequence models for speech recognition Gene-Ping Yang , Hao Tang
On the difficulty of segmenting words with attention Ramon Sanabria , Hao Tang, Sharon Goldwater
Vector-quantized autoregressive predictive coding Yu-An Chung , Hao Tang,
James Glass (best student paper award)
Audio-visual calibration with polynomial regression for 2-D projection using SVD-PHAT James Glass
A deep residual network for large-scale acoustic scene analysis James Glass
An unsupervised autoregressive model for speech representation learning Yu-An Chung ,
Wei-Ning Hsu ,
Hao Tang,
James Glass
VoiceID loss: speech enhancement for speaker verification Suwon Shon , Hao Tang,
James Glass
Time-contrastive learning based deep bottleneck features
for text-dependent speaker verification Zheng-Hua Tan ,
Hao Tang,
Suwon Shon ,
James Glass
On the inductive bias
of words in acoustics-to-word models James Glass
On training recurrent networks
with truncated backpropagation through time in speech recognition James Glass
Frame-level speaker embeddings
for text-independent speaker recognition and analysis of end-to-end model Suwon Shon , Hao Tang,
James Glass
A study of enhancement, augmentation,
and autoencoder methods for domain adaptation in distant speech recognition Wei-Ning Hsu , Francois Grondin,
James Glass
Unsupervised adaptation
with interpretable disentangled representations
for distant conversational speech recognition Wei-Ning Hsu , Hao Tang,
James Glass
End-to-end neural segmental models for speech recognition Liang Lu ,
Lingpeng Kong ,
Kevin Gimpel ,
Karen Livescu ,
Chris Dyer ,
Noah A. Smith ,
Steve Renals
Lexicon-free fingerspelling recognition from video: data, models, and signer adaptation Weiran Wang , Hao Tang, Jason Riggle,
Gregory Shakhnarovich , Diane Brentari,
Karen Livescu
Multitask learning with low-level auxiliary tasks for encoder-decoder based speech recognition Shubham Toshniwal , Hao Tang,
Liang Lu ,
Karen Livescu
ASR for under-resourced languages from probabilistic transcription Mark Hasegawa-Johnson ,
Preethi Jyothi , Daniel McCloy,
Majid Mirbagheri, Giovanni di Liberto, Amit Das,
Bradley Ekin, Chunxi Liu, Vimal Manohar, Hao Tang,
Edmund C. Lalor, Nancy Chen, Paul Hager, Tyler Kekona, Rose Sloan,
Adrian KC Lee
End-to-end training approaches for discriminative segmental models Weiran Wang ,
Kevin Gimpel ,
Karen Livescu
Efficient segmental cascades for speech recognition Weiran Wang ,
Kevin Gimpel ,
Karen Livescu
Triphone state-tying via deep canonical correlation analysis Weiran Wang ,
Hao Tang,
Karen Livescu
Adapting ASR for under-resourced languages
using mismatched transcriptions Preethi Jyothi ,
Hao Tang, Vimal Manohar, Rose Sloan, Tyler Kekona,
Mark Hasegawa-Johnson ,
Sanjeev Khudanpur (speech and language processing student paper award)
Signer-independent fingerspelling recognition
with deep neural network adaptation Weiran Wang ,
Hao Tang, Karen Livescu (best student paper of speech and language processing)
Discriminative segmental cascades
for feature-rich phone recognition Weiran Wang ,
Kevin Gimpel ,
Karen Livescu (best paper nominee)
A comparison of training approaches
for discriminative segmental models Kevin Gimpel ,
Karen Livescu
Log-linear dialog manager Shinji Watanabe ,
Tim K. Marks ,
John Hershey
Discriminative pronunciation modeling: a large-margin
feature-rich approach Joseph Keshet ,
Karen Livescu
An initial attempt for phoneme recognition using
structured SVM
Spoken term detection from bilingual spontaneous speech
using code-switched lattice-based structure for words and
subword units
Query term selection strategies for web-based Chinese factoid
question answering
