相关论文: Fast transcription of speech in low-resource langu…

Recent methods in speech and language technology pretrain very LARGE models which are fine-tuned for specific tasks. However, the benefits of such LARGE models are often limited to a few resource rich languages of the world. In this work,…

Direct speech-to-speech translation (S2ST) with discrete units leverages recent progress in speech representation learning. Specifically, a sequence of discrete representations derived in a self-supervised manner are predicted from the…

Whisper, despite being trained on 680K hours of web-scaled audio data, faces difficulty in recognising rare words like domain-specific terms, with a solution being contextual biasing through prompting. To improve upon this method, in this…

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To…

We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-time on a Nexus 5 Android smartphone. We employ a quantized…

Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on…

It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition area, but much less so in Automatic Speech Recognition (ASR).…

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference…

Speech translation for low-resource languages remains fundamentally limited by the scarcity of high-quality, diverse parallel speech data, a challenge that is especially pronounced in African linguistic contexts. To address this, we…

We propose protocols for acquiring speech materials, making them reusable for future investigations, and presenting them for subjective experiments. We also provide means to evaluate existing speech materials' compatibility with target…

We introduce Slam, a recipe for training high-quality Speech Language Models (SLMs) on a single academic GPU in 24 hours. We do so through empirical analysis of model initialisation and architecture, synthetic training data, preference…

This paper presents a novel Dialectal Sound and Vowelization Recovery framework, designed to recognize borrowed and dialectal sounds within phonologically diverse and dialect-rich languages, that extends beyond its standard orthographic…

This work focuses on modelling a speaker's accent that does not have a dedicated text-to-speech (TTS) frontend, including a grapheme-to-phoneme (G2P) module. Prior work on modelling accents assumes a phonetic transcription is available for…

Speech separation is an important problem in speech processing, which targets to separate and generate clean speech from a mixed audio containing speech from different speakers. Empowered by the deep learning technologies over…

In this work, we propose a zero-shot voice conversion method using speech representations trained with self-supervised learning. First, we develop a multi-task model to decompose a speech utterance into features such as linguistic content,…

We present the IMS-Speech, a web based tool for German and English speech transcription aiming to facilitate research in various disciplines which require accesses to lexical information in spoken language materials. This tool is based on…

Cross-lingual conversational speech summarization is an important problem, but suffers from a dearth of resources. While transcriptions exist for a number of languages, translated conversational speech is rare and datasets containing…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting module, which processes…

We present a speaker conditioned text-to-speech (TTS) system aimed at addressing challenges in generating speech for unseen speakers and supporting diverse Indian languages. Our method leverages a diffusion-based TTS architecture, where a…