Search Results for author:
Found 20 papers, 9 papers with code
Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling
Specifically, we introduce a weighted sum method, which computes a weighted sum of the embeddings of language tags, using Whisper's predicted language probabilities.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
We present Dynamic-SUPERB Phase-2, an open and evolving benchmark for the comprehensive evaluation of instruction-based universal speech models.
Representation Learning of Structured Data for Medical Foundation Models
Large Language Models (LLMs) have demonstrated remarkable performance across various domains, including healthcare.
Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
We examine critical factors in SSL that impact the budget, including model architecture, model size, and data size.
MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues
Experimental results show that LLMs can effectively model ASR noise, and incorporating this noisy data into the training process significantly improves the robustness and accuracy of medical dialogue summarization systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
uMedSum: A Unified Framework for Advancing Medical Abstractive Summarization
Current methods often sacrifice key information for faithfulness or introduce confabulations when prioritizing informativeness.
On the social bias of speech self-supervised models
We probe how various factors, such as model architecture, size, and training methodologies, influence the propagation of social bias within these models.
A Large-Scale Evaluation of Speech Foundation Models
In this work, we establish the Speech processing Universal PERformance Benchmark (SUPERB) to study the effectiveness of the paradigm for speech.
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabilities of pre-trained models by increasing task diversity and difficulty over SUPERB.
QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition
Recently, prompt-based learning for pre-trained language models has succeeded in few-shot Named Entity Recognition (NER) by exploiting prompts as task guidance to increase label efficiency.
Don't speak too fast: The impact of data bias on self-supervised speech models
Self-supervised Speech Models (S3Ms) have been proven successful in many speech downstream tasks, like ASR.
Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning
This work is among the first to perform adversarial defense for ASV without knowing the specific attack algorithms.
SUPERB: Speech processing Universal PERformance Benchmark
SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data.
Adversarial defense for automatic speaker verification by cascaded self-supervised learning models
Automatic speaker verification (ASV) is one of the core technologies in biometric identification.
TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
We present a large-scale comparison of various self-supervised models.
Understanding Self-Attention of Self-Supervised Audio Transformers
Self-supervised Audio Transformers (SAT) enable great success in many downstream speech applications like ASR, but how they work has not been widely explored yet.
Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning
To explore this issue, we proposed to employ Mockingjay, a self-supervised learning based model, to protect anti-spoofing models against adversarial attacks in the black-box scenario.
Towards Robust Neural Vocoding for Speech Generation: A Survey
We found out that the speaker variety is much more important for achieving a universal vocoder than the language.
Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
We present Mockingjay as a new speech representation learning approach, where bidirectional Transformer encoders are pre-trained on a large amount of unlabeled speech.
Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
We found that the proposed encoding method offers automatic extraction of speech content from speaker style, and is sufficient to cover full linguistic content in a given language.
