23 citations · 48 across the 20 of their papers we have counts for
22 papers
Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining
Takaaki Saeki, Soumi Maiti, Xinjian Li +3
While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text…
Textless Direct Speech-to-Speech Translation with Discrete Speech Representation
Xinjian Li, Ye Jia, Chung-Cheng Chiu
Research on speech-to-speech translation (S2ST) has progressed rapidly in recent years. Many end-to-end systems have been proposed and show advantages over conventional cascade sys…
ASR2K: Speech Recognition for Around 2000 Languages without Audio
Xinjian Li, Florian Metze, David R Mortensen +2
Most recent speech recognition models rely on large supervised datasets, which are unavailable for many low-resource languages. In this work, we present a speech recognition pipeli…
On Adversarial Robustness of Large-scale Audio Visual Learning
Juncheng B Li, Shuhui Qu, Xinjian Li +2
As audio-visual systems are being deployed for safety-critical tasks such as surveillance and malicious content filtering, their robustness remains an under-studied area. Existing…
Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations
Junning Liu, Zijie Xia, Yu Lei +2
There has been many studies on improving the efficiency of shared learning in Multi-Task Learning(MTL). Previous work focused on the "micro" sharing perspective for a small number…
On Prosody Modeling for ASR+TTS based Voice Conversion
Wen-Chin Huang, Tomoki Hayashi, Xinjian Li +2
In voice conversion (VC), an approach showing promising results in the latest voice conversion challenge (VCC) 2020 is to first use an automatic speech recognition (ASR) model to t…
Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Kathleen Siminyu, Xinjian Li, Antonios Anastasopoulos +3
Models pre-trained on multiple languages have shown significant promise for improving speech recognition, particularly for low-resource languages. In this work, we focus on phoneme…
Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments
David R. Mortensen, Jordan Picone, Xinjian Li +1
There is growing interest in ASR systems that can recognize phones in a language-independent fashion. There is additionally interest in building language technologies for low-resou…
Acoustics Based Intent Recognition Using Discovered Phonetic Units for Low Resource Languages
Akshat Gupta, Xinjian Li, Sai Krishna Rallabandi +1
With recent advancements in language technologies, humans are now speaking to devices. Increasing the reach of spoken language technologies requires building systems in local langu…
Revisiting Factorizing Aggregated Posterior in Learning Disentangled Representations
Ze Cheng, Juncheng Li, Chenxu Wang +4
In the problem of learning disentangled representations, one of the promising methods is to factorize aggregated posterior by penalizing the total correlation of sampled latent var…
Semi-Supervised Recognition under a Noisy and Fine-grained Dataset
Cheng Cui, Zhi Ye, Yangxi Li +7
Simi-Supervised Recognition Challenge-FGVC7 is a challenging fine-grained recognition competition. One of the difficulties of this competition is how to use unlabeled data. We adop…
A Summary of the First Workshop on Language Technology for Language Documentation and Revitalization
Graham Neubig, Shruti Rijhwani, Alexis Palmer +21
Despite recent advances in natural language processing and other language technology, the application of such technology to language documentation and conservation has been limited…
AlloVera: A Multilingual Allophone Database
David R. Mortensen, Xinjian Li, Patrick Littell +6
We introduce a new resource, AlloVera, which provides mappings from 218 allophones to phonemes for 14 languages. Phonemes are contrastive phonological units, and allophones are the…
Universal Phone Recognition with a Multilingual Allophone System
Xinjian Li, Siddharth Dalmia, Juncheng Li +8
Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages. Multilingual acoustic models, however, genera…
Towards Zero-shot Learning for Automatic Phonemic Transcription
Xinjian Li, Siddharth Dalmia, David R. Mortensen +3
Automatic phonemic transcription tools are useful for low-resource language documentation. However, due to the lack of training sets, only a tiny fraction of languages have phonemi…
Adversarial Music: Real World Audio Adversary Against Wake-word Detection System
Juncheng B. Li, Shuhui Qu, Xinjian Li +3
Voice Assistants (VAs) such as Amazon Alexa or Google Assistant rely on wake-word detection to respond to people's commands, which could potentially be vulnerable to audio adversar…
SANTLR: Speech Annotation Toolkit for Low Resource Languages
Xinjian Li, Zhong Zhou, Siddharth Dalmia +2
While low resource speech recognition has attracted a lot of attention from the speech community, there are a few tools available to facilitate low resource speech collection. In t…
Multilingual Speech Recognition with Corpus Relatedness Sampling
Xinjian Li, Siddharth Dalmia, Alan W. Black +1
Multilingual acoustic models have been successfully applied to low-resource speech recognition. Most existing works have combined many small corpora together and pretrained a multi…
The ARIEL-CMU Systems for LoReHLT18
Aditi Chaudhary, Siddharth Dalmia, Junjie Hu +27
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery a…
Phoneme Level Language Models for Sequence Based Low Resource ASR
Siddharth Dalmia, Xinjian Li, Alan W Black +1
Building multilingual and crosslingual models help bring different languages together in a language universal space. It allows models to share parameters and transfer knowledge acr…
Real-time Neural-based Input Method
Jiali Yao, Raphael Shu, Xinjian Li +2
The input method is an essential service on every mobile and desktop devices that provides text suggestions. It converts sequential keyboard inputs to the characters in its target…
Domain Robust Feature Extraction for Rapid Low Resource ASR Development
Siddharth Dalmia, Xinjian Li, Florian Metze +1
Developing a practical speech recognizer for a low resource language is challenging, not only because of the (potentially unknown) properties of the language, but also because test…