相关论文: Efficient Dynamic WFST Decoding for Personalized L…

Graph clustering under the framework of differential privacy, which aims to process graph-structured data while protecting individual privacy, has been receiving increasing attention. Despite significant achievements in current research,…

End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which…

Linear sketches have been widely adopted to process fast data streams, and they can be used to accurately answer frequency estimation, approximate top K items, and summarize data distributions. When data are sensitive, it is desirable to…

We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a recent privacy-preserving approach suitable for solving downstream tasks with sensitive data. Existing work has demonstrated that high accuracy…

Code-switching in automatic speech recognition (ASR) is an important challenge due to globalization. Recent research in multilingual ASR shows potential improvement over monolingual systems. We study key issues related to multilingual…

Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not test this solution for direct…

Endowing chatbots with a consistent persona is essential to an engaging conversation, yet it remains an unresolved challenge. In this work, we propose a new retrieval-enhanced approach for personalized response generation. Specifically, we…

Among parameter-efficient fine-tuning methods, freezing has emerged as a popular strategy for speeding up training, reducing catastrophic forgetting, and improving downstream performance. We investigate the impact of freezing the decoder in…

Diffusion models have shown promising results in speech enhancement, using a task-adapted diffusion process for the conditional generation of clean speech given a noisy mixture. However, at test time, the neural network used for score…

This paper presents novel Weighted Finite-State Transducer (WFST) topologies to implement Connectionist Temporal Classification (CTC)-like algorithms for automatic speech recognition. Three new CTC variants are proposed: (1) the…

We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or finetuning. To trading off accuracy and latency, DET…

While Diffusion Generative Models have achieved great success on image generation tasks, how to efficiently and effectively incorporate them into speech generation especially translation tasks remains a non-trivial problem. Specifically,…

Pre-trained language models have achieved huge improvement on many NLP tasks. However, these methods are usually designed for written text, so they do not consider the properties of spoken language. Therefore, this paper aims at…

In this work, we propose an error correction framework, named DiaCorrect, to refine the output of a diarization system in a simple yet effective way. This method is inspired by error correction techniques in automatic speech recognition.…

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the…

Recently, dynamic computation methods have shown notable acceleration for Large Language Models (LLMs) by skipping several layers of computations through elaborate heuristics or additional predictors. However, in the decoding process of…

Large Language Diffusion Models (LLDMs) benefit from a flexible decoding mechanism that enables parallelized inference and controllable generations over autoregressive models. Yet such flexibility introduces a critical challenge: inference…

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models…

Current works in the generation of personalized dialogue primarily contribute to the agent presenting a consistent personality and driving a more informative response. However, we found that the generated responses from most previous models…

This work proposes a grammar-based chunking strategy that segments input streams into semantically complete units by parsing dependency relations (e.g., noun phrase boundaries, verb-object structures) and punctuation features. The method…