no code implementations • 29 Feb 2024 • Takaaki Saeki, Gary Wang, Nobuyuki Morioka, Isaac Elias, Kyle Kastner, Andrew Rosenberg, Bhuvana Ramabhadran, Heiga Zen, Françoise Beaufays, Hadar Shemtov
Without any transcribed speech in a new language, this TTS model can generate intelligible speech in >30 unseen languages (CER difference of <10% to ground truth).
no code implementations • 8 Jan 2024 • Christopher Li, Gary Wang, Kyle Kastner, Heng Su, Allen Chen, Andrew Rosenberg, Zhehuai Chen, Zelin Wu, Leonid Velikovich, Pat Rondon, Diamantino Caseiro, Petar Aleksic
In this paper, we eliminate the hypothesis-audio mismatch problem by querying the correction database directly using embeddings derived from the utterance audio; the embeddings of the utterance audio and candidate corrections are produced by multimodal speech-text embedding networks trained to place the embedding of the audio of an utterance and the embedding of its corresponding textual transcript close together.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 14 Aug 2023 • Yochai Blau, Rohan Agrawal, Lior Madmony, Gary Wang, Andrew Rosenberg, Zhehuai Chen, Zorik Gekhman, Genady Beryozkin, Parisa Haghani, Bhuvana Ramabhadran
We use text-injection to improve the recognition of PII categories by including fake textual substitutes of PII categories in the training data using a text injection method.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 14 Aug 2023 • Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Kartik Audhkhasi
O-1 achieves 13\% to 25\% relative improvement over EMBR on the various datasets that SpeechStew comprises of, and a 12\% relative gap reduction with respect to the oracle WER over EMBR training on the in-house dataset.
no code implementations • 11 Aug 2023 • Cal Peyser, Zhong Meng, Ke Hu, Rohit Prabhavalkar, Andrew Rosenberg, Tara N. Sainath, Michael Picheny, Kyunghyun Cho
The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly.
no code implementations • 27 Apr 2023 • Gary Wang, Kyle Kastner, Ankur Bapna, Zhehuai Chen, Andrew Rosenberg, Bhuvana Ramabhadran, Yu Zhang
Recently, a number of approaches to train speech models by incorpo-rating text into end-to-end models have been developed, with Mae-stro advancing state-of-the-art automatic speech recognition (ASR)and Speech Translation (ST) performance.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 2 Mar 2023 • Yu Zhang, Wei Han, James Qin, Yongqiang Wang, Ankur Bapna, Zhehuai Chen, Nanxin Chen, Bo Li, Vera Axelrod, Gary Wang, Zhong Meng, Ke Hu, Andrew Rosenberg, Rohit Prabhavalkar, Daniel S. Park, Parisa Haghani, Jason Riesa, Ginger Perng, Hagen Soltau, Trevor Strohman, Bhuvana Ramabhadran, Tara Sainath, Pedro Moreno, Chung-Cheng Chiu, Johan Schalkwyk, Françoise Beaufays, Yonghui Wu
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 16 Feb 2023 • Zhong Meng, Weiran Wang, Rohit Prabhavalkar, Tara N. Sainath, Tongzhou Chen, Ehsan Variani, Yu Zhang, Bo Li, Andrew Rosenberg, Bhuvana Ramabhadran
We propose JEIT, a joint end-to-end (E2E) model and internal language model (ILM) training method to inject large-scale unpaired text into ILM during E2E training which improves rare-word speech recognition.
no code implementations • 27 Oct 2022 • Takaaki Saeki, Heiga Zen, Zhehuai Chen, Nobuyuki Morioka, Gary Wang, Yu Zhang, Ankur Bapna, Andrew Rosenberg, Bhuvana Ramabhadran
This paper proposes Virtuoso, a massively multilingual speech-text joint semi-supervised learning framework for text-to-speech synthesis (TTS) models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 19 Oct 2022 • Gary Wang, Ekin D. Cubuk, Andrew Rosenberg, Shuyang Cheng, Ron J. Weiss, Bhuvana Ramabhadran, Pedro J. Moreno, Quoc V. Le, Daniel S. Park
Data augmentation is a ubiquitous technique used to provide robustness to automatic speech recognition (ASR) training.
Ranked #1 on Speech Recognition on CHiME-6 eval
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 18 Oct 2022 • Zhehuai Chen, Ankur Bapna, Andrew Rosenberg, Yu Zhang, Bhuvana Ramabhadran, Pedro Moreno, Nanxin Chen
First, we show that by combining speech representations with byte-level text representations and use of language embeddings, we can dramatically reduce the Character Error Rate (CER) on languages with no supervised speech from 64. 8\% to 30. 8\%, a relative reduction of 53\%.
no code implementations • 15 Sep 2022 • Gary Wang, Andrew Rosenberg, Bhuvana Ramabhadran, Fadi Biadsy, Yinghui Huang, Jesse Emond, Pedro Moreno Mengibar
For ASR augmentation, it is necessary that the VC model be robust to a wide range of input speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 16 May 2022 • Alëna Aksënova, Zhehuai Chen, Chung-Cheng Chiu, Daan van Esch, Pavel Golik, Wei Han, Levi King, Bhuvana Ramabhadran, Andrew Rosenberg, Suzan Schwartz, Gary Wang
However, there are not enough data sets for accented speech, and for the ones that are already available, more training approaches need to be explored to improve the quality of accented speech recognition.
no code implementations • 7 Apr 2022 • Zhehuai Chen, Yu Zhang, Andrew Rosenberg, Bhuvana Ramabhadran, Pedro Moreno, Ankur Bapna, Heiga Zen
Self-supervised learning from speech signals aims to learn the latent structure inherent in the signal, while self-supervised learning from text attempts to capture lexical information.
no code implementations • 23 Mar 2022 • Fadi Biadsy, Youzheng Chen, Xia Zhang, Oleg Rybakov, Andrew Rosenberg, Pedro J. Moreno
We also show that learning a speaker-embedding space can scale further and reduce the amount of personalization training data required per speaker.
no code implementations • 24 Feb 2022 • Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Yu Zhang, Pedro Moreno
They treat all unsupervised speech samples with equal weight, which hinders learning as not all samples have relevant information to learn meaningful representations.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 27 Aug 2021 • Zhehuai Chen, Yu Zhang, Andrew Rosenberg, Bhuvana Ramabhadran, Gary Wang, Pedro Moreno
The proposed method, tts4pretrain complements the power of contrastive learning in self-supervision with linguistic/lexical representations derived from synthesized speech, effectively learning from untranscribed speech and unspoken text.
no code implementations • 6 Feb 2020 • Guangzhi Sun, Yu Zhang, Ron J. Weiss, Yuan Cao, Heiga Zen, Andrew Rosenberg, Bhuvana Ramabhadran, Yonghui Wu
Recent neural text-to-speech (TTS) models with fine-grained latent features enable precise control of the prosody of synthesized speech.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 25 Sep 2019 • Andrew Rosenberg, Yu Zhang, Bhuvana Ramabhadran, Ye Jia, Pedro Moreno, Yonghui Wu, Zelin Wu
Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific, human speech that is used to train speech recognizers.
4 code implementations • 9 Jul 2019 • Yu Zhang, Ron J. Weiss, Heiga Zen, Yonghui Wu, Zhifeng Chen, RJ Skerry-Ryan, Ye Jia, Andrew Rosenberg, Bhuvana Ramabhadran
We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages.
no code implementations • 7 Feb 2018 • Xuesong Yang, Kartik Audhkhasi, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Mark Hasegawa-Johnson
The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 13 Jan 2017 • Kartik Audhkhasi, Andrew Rosenberg, Abhinav Sethy, Bhuvana Ramabhadran, Brian Kingsbury
The first sub-system is a recurrent neural network (RNN)-based acoustic auto-encoder trained to reconstruct the audio through a finite-dimensional representation.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • LREC 2016 • Denys Katerenchuk, Andrew Rosenberg
We propose a new measure, a modification of the popular nDCG algorithm, named rankDCG, that addresses these problems.
no code implementations • MediaEval 2015 Workshop 2015 • Min Ma, Andrew Rosenberg
This paper describes two query-by-example systems developed by Speech Lab, Queens College (CUNY).
Ranked #49 on Keyword Spotting on QUESST