Related papers: The Esethu Framework: Reimagining Sustainable Data…

Much recent work on Spoken Language Understanding (SLU) falls short in at least one of three ways: models were trained on oracle text input and neglected the Automatics Speech Recognition (ASR) outputs, models were trained to predict only…

While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language…

This paper presents SaSLaW, a spontaneous dialogue speech corpus containing synchronous recordings of what speakers speak, listen to, and watch. Humans consider the diverse environmental factors and then control the features of their…

Benchmark datasets have a significant impact on accelerating research in programming language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster machine learning research for program understanding and generation.…

Target Speech Extraction (TSE) traditionally relies on explicit clues about the speaker's identity like enrollment audio, face images, or videos, which may not always be available. In this paper, we propose a text-guided TSE model StyleTSE…

We propose TES-VC (Text-driven Environment and Speaker controllable Voice Conversion), a text-driven voice conversion framework with independent control of speaker timbre and environmental acoustics. TES-VC processes simultaneous text…

Automatic Speech Recognition (ASR) for low-resource Dravidian languages like Telugu and Kannada faces significant challenges in specialized medical domains due to limited annotated data and morphological complexity. This work proposes a…

This work introduces Sample-Efficient Speech Diffusion (SESD), an algorithm for effective speech synthesis in modest data regimes through latent diffusion. It is based on a novel diffusion architecture, that we call U-Audio Transformer…

Building Automatic Speech Recognition (ASR) systems for code-switched speech has recently gained renewed attention due to the widespread use of speech technologies in multilingual communities worldwide. End-to-end ASR systems are a natural…

Robust speech recognition systems rely on cloud service providers for inference. It needs to ensure that an untrustworthy provider cannot deduce the sensitive content in speech. Sanitization can be done on speech content keeping in mind…

EEG-based tinnitus classification is a valuable tool for tinnitus diagnosis, research, and treatments. Most current works are limited to a single dataset where data patterns are similar. But EEG signals are highly non-stationary, resulting…

End-to-end (E2E) spoken language understanding (SLU) is constrained by the cost of collecting speech-semantics pairs, especially when label domains change. Hence, we explore \textit{zero-shot} E2E SLU, which learns E2E SLU without…

Target speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture. Most existing TSE models rely on discriminative methods, typically predicting a time-frequency spectrogram mask for the…

Domain-specific Visually Rich Document Understanding (VRDU) presents significant challenges due to the complexity and sensitivity of documents in fields such as medicine, finance, and material science. Existing Large (Multimodal) Language…

This paper presents an overview of a program designed to address the growing need for developing freely available speech resources for under-represented languages. At present we have released 38 datasets for building text-to-speech and…

This study aims at designing an environment-aware text-to-speech (TTS) system that can generate speech to suit specific acoustic environments. It is also motivated by the desire to leverage massive data of speech audio from heterogeneous…

Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between…

Automatic speech recognition (ASR) for dysarthric speech remains challenging due to data scarcity, particularly in non-English languages. To address this, we fine-tune a voice conversion model on English dysarthric speech (UASpeech) to…

Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models are composed of modular building blocks that are flexible and…

This work explores fine-tuning OpenAI's Whisper automatic speech recognition (ASR) model for Amharic, a low-resource language, to improve transcription accuracy. While the foundational Whisper model struggles with Amharic due to limited…