Related papers: CSS10: A Collection of Single Speaker Speech Datas…

Text-to-Speech (TTS) models can generate natural, human-like speech across multiple languages by transforming phonemes into waveforms. However, multilingual TTS remains challenging due to discrepancies in phoneme vocabularies and variations…

The performance of speaker verification systems degrades significantly under language mismatch, a critical challenge exacerbated by the field's reliance on English-centric data. To address this, we propose the TidyVoice Challenge for…

In this paper, we propose a personalized neural speech codec, envisioning that personalization can reduce the model complexity or improve perceptual speech quality. Despite the common usage of speech codecs where only a single talker is…

Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing drastically benefitted from SSL as most of the current…

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping…

The audio data is increasing day by day throughout the globe with the increase of telephonic conversations, video conferences and voice messages. This research provides a mechanism for identifying a speaker in an audio file, based on the…

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

This document provides a brief description of the National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) conversational telephone speech (CTS) Superset. The CTS Superset has been created in an attempt to…

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).…

Joint speech-language training is challenging due to the large demand for training data and GPU consumption, as well as the modality gap between speech and language. We present ComSL, a speech-language model built atop a composite…

As speech generation technology advances, the risk of misuse through deepfake audio has become a pressing concern, which underscores the critical need for robust detection systems. However, many existing speech deepfake datasets are limited…

We introduce SIFT (Speech Instruction Fine-Tuning), a 50M-example dataset designed for instruction fine-tuning and pre-training of speech-text large language models (LLMs). SIFT-50M is built from publicly available speech corpora, which…

Collecting high-quality studio recordings of audio is challenging, which limits the language coverage of text-to-speech (TTS) systems. This paper proposes a framework for scaling a multilingual TTS model to 100+ languages using found data…

The Speech Wikimedia Dataset is a publicly available compilation of audio with transcriptions extracted from Wikimedia Commons. It includes 1780 hours (195 GB) of CC-BY-SA licensed transcribed speech from a diverse set of scenarios and…

Personalization of speech models on mobile devices (on-device personalization) is an active area of research, but more often than not, mobile devices have more text-only data than paired audio-text data. We explore training a personalized…

The scarcity of large-scale classroom speech data has hindered the development of AI-driven speech models for education. Public classroom datasets remain limited, and the lack of a dedicated classroom noise corpus prevents the use of…

Existing text-to-speech systems predominantly focus on single-sentence synthesis and lack adequate contextual modeling as well as fine-grained performance control capabilities for generating coherent multicast audiobooks. To address these…

We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models. The dataset consists of 1.1k human-written natural language descriptions…

Speech Large Language Models (SLLMs) have rapidly expanded, supporting a wide range of tasks. These models are typically evaluated using text prompts, which may not reflect real-world scenarios where users interact with speech. To address…