Related papers: STaR: Distilling Speech Temporal Relation for Ligh…

Self-supervised learning (SSL) is a powerful technique for learning representations from unlabeled data. Transformer based models such as HuBERT, which consist a feature extractor and transformer layers, are leading the field in the speech…

Self-supervised learning (SSL) is seen as a very promising approach with high performance for several speech downstream tasks. Since the parameters of SSL models are generally so large that training and inference require a lot of memory and…

Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…

The goal of this paper is to introduce SPADE, a framework for Structured Pruning and Adaptive Distillation for Efficient Large Language Model-based text-to-speech (LLM-TTS). Recent LLM-TTS systems achieve strong controllability and…

In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR). An ASR model with decent performance can be realized by fine-tuning an SSL model with…

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…

Syllables are compositional units of spoken language that efficiently structure human speech perception and production. However, current neural speech representations lack such structure, resulting in dense token sequences that are costly…

Hidden-unit BERT (HuBERT) is a widely-used self-supervised learning (SSL) model in speech processing. However, we argue that its fixed 20ms resolution for hidden representations would not be optimal for various speech-processing tasks since…

SUPERB was proposed to evaluate the generalizability of self-supervised learning (SSL) speech models across various tasks. However, it incurs high computational costs due to the large datasets and diverse tasks. In this paper, we introduce…

Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…

Massively multilingual Transformers (MMTs), such as mBERT and XLM-R, are widely used for cross-lingual transfer learning. While these are pretrained to represent hundreds of languages, end users of NLP systems are often interested only in…

Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting…

Natural Language Processing models like BERT can provide state-of-the-art word embeddings for downstream NLP tasks. However, these models yet to perform well on Semantic Textual Similarity, and may be too large to be deployed as lightweight…

Diffusion model, as a new generative model which is very popular in image generation and audio synthesis, is rarely used in speech enhancement. In this paper, we use the diffusion model as a module for stochastic refinement. We propose…

We propose the joint speech translation and recognition (JSTAR) model that leverages the fast-slow cascaded encoder architecture for simultaneous end-to-end automatic speech recognition (ASR) and speech translation (ST). The model is…

This paper explores the use of ASR-pretrained Conformers for speaker verification, leveraging their strengths in modeling speech signals. We introduce three strategies: (1) Transfer learning to initialize the speaker embedding network,…

Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically,…

Self-supervised learning (SSL) has achieved great success in speech-related tasks. While Transformer and Conformer architectures have dominated SSL backbones, encoders like Zipformer, which excel in automatic speech recognition (ASR),…

ML-SUPERB evaluates self-supervised learning (SSL) models on the tasks of language identification and automatic speech recognition (ASR). This benchmark treats the models as feature extractors and uses a single shallow downstream model,…