32 citations · 102 across the 19 of their papers we have counts for
20 papers
FA-Bench: A Benchmark for Phone- and Word-Level Timestamp Accuracy in Forced Alignment and ASR on Clean and Noisy Speech
Wei Chu, Yuanzhe Dong, Ke Tan +11
Forced alignment estimates the timestamps of each word, phone or character in speech given its transcript. Published comparisons normalize transcripts, split the data and match bou…
OleSpeech-IV: A Large-Scale Multispeaker and Multilingual Conversational Speech Dataset with Diverse Topics
Wei Chu, Yuanzhe Dong, Ke Tan +7
OleSpeech-IV dataset is a large-scale multispeaker and multilingual conversational speech dataset with diverse topics. The audio content comes from publicly-available English podca…
SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASR
Natarajan Balaji Shankar, Ruchao Fan, Abeer Alwan
Recently, speech foundation models have gained popularity due to their superiority in finetuning downstream ASR tasks. However, models finetuned on certain domains, such as LibriSp…
Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models
Ruchao Fan, Natarajan Balaji Shankar, Abeer Alwan
Speech foundation models (SFMs) have achieved state-of-the-art results for various speech tasks in supervised (e.g. Whisper) or self-supervised systems (e.g. WavLM). However, the p…
UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models
Ruchao Fan, Natarajan Balaji Shanka, Abeer Alwan
Non-autoregressive automatic speech recognition (NASR) models have gained attention due to their parallelism and fast inference. The encoder-based NASR, e.g. connectionist temporal…
Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASR
Ruchao Fan, Yunzheng Zhu, Jinhan Wang +1
Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased attention in the automatic speech recognition (ASR) community. Typical SSL methods include…
A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition
Ruchao Fan, Wei Chu, Peng Chang +1
Recently, end-to-end models have been widely used in automatic speech recognition (ASR) systems. Two of the most representative approaches are connectionist temporal classification…
Acoustic-aware Non-autoregressive Spell Correction with Mask Sample Decoding
Ruchao Fan, Guoli Ye, Yashesh Gaur +1
Masked language model (MLM) has been widely used for understanding tasks, e.g. BERT. Recently, MLM has also been used for generation tasks. The most popular one in speech is using…
CTCBERT: Advancing Hidden-unit BERT with CTC Objectives
Ruchao Fan, Yiming Wang, Yashesh Gaur +1
In this work, we present a simple but effective method, CTCBERT, for advancing hidden-unit BERT (HuBERT). HuBERT applies a frame-level cross-entropy (CE) loss, which is similar to…
DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children's ASR
Ruchao Fan, Abeer Alwan
Self-supervised learning (SSL) in the pretraining stage using un-annotated speech data has been successful in low-resource automatic speech recognition (ASR) tasks. However, models…
Towards Better Meta-Initialization with Task Augmentation for Kindergarten-aged Speech Recognition
Yunzheng Zhu, Ruchao Fan, Abeer Alwan
Children's automatic speech recognition (ASR) is always difficult due to, in part, the data scarcity problem, especially for kindergarten-aged kids. When data are scarce, the model…
LPC Augment: An LPC-Based ASR Data Augmentation Algorithm for Low and Zero-Resource Children's Dialects
Alexander Johnson, Ruchao Fan, Robin Morris +1
This paper proposes a novel linear prediction coding-based data aug-mentation method for children's low and zero resource dialect ASR. The data augmentation procedure consists of p…
An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognition
Ruchao Fan, Wei Chu, Peng Chang +2
Non-autoregressive mechanisms can significantly decrease inference time for speech transformers, especially when the single step variant is applied. Previous work on CTC alignment-…
Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System
Jinhan Wang, Yunzheng Zhu, Ruchao Fan +2
This paper describes the SPAPL system for the INTERSPEECH 2021 Challenge: Shared Task on Automatic Speech Recognition for Non-Native Children's Speech in German. ~ 5 hours of trans…
Fundamental Frequency Feature Normalization and Data Augmentation for Child Speech Recognition
Gary Yeung, Ruchao Fan, Abeer Alwan
Automatic speech recognition (ASR) systems for young children are needed due to the importance of age-appropriate educational technology. Because of the lack of publicly available…
Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR
Ruchao Fan, Amber Afshan, Abeer Alwan
We present a bidirectional unsupervised model pre-training (UPT) method and apply it to children's automatic speech recognition (ASR). An obstacle to improving child ASR is the sca…
CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognition
Ruchao Fan, Wei Chu, Peng Chang +1
We propose a CTC alignment-based single step non-autoregressive transformer (CASS-NAT) for speech recognition. Specifically, the CTC alignment contains the information of (a) the n…
Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification
Vijay Ravi, Ruchao Fan, Amber Afshan +2
In this paper, we propose a novel way of addressing text-dependent automatic speaker verification (TD-ASV) by using a shared-encoder with task-specific decoders. An autoregressive…
Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding
Pan Zhou, Ruchao Fan, Wei Chen +1
Transformer has shown promising results in many sequence to sequence transformation tasks recently. It utilizes a number of feed-forward self-attention layers to replace the recurr…
An Online Attention-based Model for Speech Recognition
Ruchao Fan, Pan Zhou, Wei Chen +2
Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular i…