Related papers: Real-time Speech Interruption Analysis: From Cloud…

Most automatic speech processing systems operate in ``open loop'' mode without user feedback about who said what, yet human-in-the-loop workflows can potentially enable higher accuracy. We propose an LLM-assisted in-meeting speaker…

With the advances in speech communication systems such as online conferencing applications, we can seamlessly work with people regardless of where they are. However, during online meetings, speech quality can be significantly affected by…

A major focus of recent research in spoken language understanding (SLU) has been on the end-to-end approach where a single model can predict intents directly from speech inputs without intermediate transcripts. However, this approach…

Current speech-based LLMs are predominantly trained on extensive ASR and TTS datasets, excelling in tasks related to these domains. However, their ability to handle direct speech-to-speech conversations remains notably constrained. These…

Low power deep learning accelerators on the speech processing enable real-time applications on edge devices. However, most of the existing accelerators suffer from high power consumption and focus on image applications only. This paper…

Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is…

Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…

Speech enhancement models have greatly progressed in recent years, but still show limits in perceptual quality of their speech outputs. We propose an objective for perceptual quality based on temporal acoustic parameters. These are…

The ConferencingSpeech 2021 challenge is proposed to stimulate research on far-field multi-channel speech enhancement for video conferencing. The challenge consists of two separate tasks: 1) Task 1 is multi-channel speech enhancement with…

As deep speech enhancement algorithms have recently demonstrated capabilities greatly surpassing their traditional counterparts for suppressing noise, reverberation and echo, attention is turning to the problem of packet loss concealment…

State-of-the-art text-to-speech (TTS) systems have utilized pretrained language models (PLMs) to enhance prosody and create more natural-sounding speech. However, while PLMs have been extensively researched for natural language…

Speech-to-speech translation (S2ST) converts input speech to speech in another language. A challenge of delivering S2ST in real time is the accumulated delay between the translation and speech synthesis modules. While recently incremental…

Speech understanding is essential for interpreting the diverse forms of information embedded in spoken language, including linguistic, paralinguistic, and non-linguistic cues that are vital for effective human-computer interaction. The…

In recent years, deep learning based source separation has achieved impressive results. Most studies, however, still evaluate separation models on synthetic datasets, while the performance of state-of-the-art techniques on in-the-wild…

Recent advancements in Large Language Models (LLMs) have generated growing interest in their structured reasoning capabilities, particularly in tasks involving abstraction and pattern recognition. The Abstraction and Reasoning Corpus (ARC)…

Federated learning is a communication-efficient training process that alternates between local training at the edge devices and averaging the updated local model at the central server. Nevertheless, it is impractical to achieve a perfect…

This paper introduces a speech enhancement solution tailored for true wireless stereo (TWS) earbuds on-device usage. The solution was specifically designed to support conversations in noisy environments, with active noise cancellation (ANC)…

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to grammatical errors, disfluency, and other…

Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method to camouflage a person's voice over-the-air from these…

Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However,…