相关论文: On-device Streaming Discrete Speech Units

Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number…

In recent advancements in high-fidelity image generation, Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a key player. However, their application at high resolutions presents significant computational challenges. Current…

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

Strong presentation skills are valuable and sought-after in workplace and classroom environments alike. Of the possible improvements to vocal presentations, disfluencies and stutters in particular remain one of the most common and prominent…

In this paper, we propose a novel method for speaker adaptation in lip reading, motivated by two observations. Firstly, a speaker's own characteristics can always be portrayed well by his/her few facial images or even a single image with…

In this study, we aim to explore efficient tuning methods for speech self-supervised learning. Recent studies show that self-supervised learning (SSL) can learn powerful representations for different speech tasks. However, fine-tuning…

Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited…

Distributed microphone array (DMA) is a promising next-generation platform for speech interaction, where speech enhancement (SE) is still required to improve the speech quality in noisy cases. Existing SE methods usually first gather raw…

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

Audio-based stuttering systems to date have been trained for detection -- what disfluency is present now -- leaving prediction, the capability needed for closed-loop intervention, unstudied at deployable scale. We train a 616K-parameter CNN…

Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases.…

Due to the lack of target speech annotations in real-recorded far-field conversational datasets, speech enhancement (SE) models are typically trained on simulated data. However, the trained models often perform poorly in real-world…

This paper proposes a low algorithmic latency adaptation of the deep clustering approach to speaker-independent speech separation. It consists of three parts: a) the usage of long-short-term-memory (LSTM) networks instead of their…

To further reduce the complexity of lightweight speech enhancement models, we introduce a gating-based Dynamically Slimmable Network (DSN). The DSN comprises static and dynamic components. For architecture-independent applicability, we…

Representing speech and audio signals in discrete units has become a compelling alternative to traditional high-dimensional feature vectors. Numerous studies have highlighted the efficacy of discrete units in various applications such as…

Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…

While mobile devices provide ever more compute power, improvements in DRAM bandwidth are much slower. This is unfortunate for large language model (LLM) token generation, which is heavily memory-bound. Previous work has proposed to leverage…

Recently, several studies reported that dot-product selfattention (SA) may not be indispensable to the state-of-theart Transformer models. Motivated by the fact that dense synthesizer attention (DSA), which dispenses with dot products and…

Speaker clustering is the task of forming speaker-specific groups based on a set of utterances. In this paper, we address this task by using Dominant Sets (DS). DS is a graph-based clustering algorithm with interesting properties that fits…

Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings containing multiple speakers using the Streaming Unmixing and…