Related papers: Spatial LibriSpeech: An Augmented Dataset for Spat…
Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent advances in speech…
Ambisonics i.e., a full-sphere surround sound, is quintessential with 360-degree visual content to provide a realistic virtual reality (VR) experience. While 360-degree visual content capture gained a tremendous boost recently, the…
We address the challenge of making spatial audio datasets by proposing a shared mechanized recording space that can run custom acoustic experiments: a Mechatronic Acoustic Research System (MARS). To accommodate a wide variety of…
This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior studies on speech separation use pre-segmented signals of artificially mixed speech utterances which are mostly \emph{fully}…
Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…
This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving…
Spatial audio is essential for enhancing the immersiveness of audio-visual experiences, yet its production typically demands complex recording systems and specialized expertise. In this work, we address a novel problem of generating…
Sound capture by microphone arrays opens the possibility to exploit spatial, in addition to spectral, information for diarization and signal enhancement, two important tasks in meeting transcription. However, there is no one-to-one mapping…
This paper enhances dysarthric and dysphonic speech recognition by fine-tuning pretrained automatic speech recognition (ASR) models on the 2023-10-05 data package of the Speech Accessibility Project (SAP), which contains the speech of 253…
Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS…
Speech clarity and spatial audio immersion are the two most critical factors in enhancing remote conferencing experiences. Existing methods are often limited: either due to the lack of spatial information when using only one microphone, or…
This paper describes a spatial-aware speaker diarization system for the multi-channel multi-party meeting. The diarization system obtains direction information of speaker by microphone array. Speaker spatial embedding is generated by…
With 4.5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition. We propose data selection techniques to…
Spatial understanding is a crucial capability that enables robots to perceive their surroundings, reason about their environment, and interact with it meaningfully. In modern robotics, these capabilities are increasingly provided by…
Geometrical approaches for room acoustics simulation have the advantage of requiring limited computational resources while still achieving a high perceptual plausibility. A common approach is using the image source model for direct and…
Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training E2E ASR models that get the performance benefits of external text data without…
Slovak remains a low-resource language for automatic speech recognition (ASR), with fewer than 100 hours of publicly available training data. We present SloPal, a comprehensive Slovak parliamentary corpus comprising 330,000…
We present ASR Bundestag, a dataset for automatic speech recognition in German, consisting of 610 hours of aligned audio-transcript pairs for supervised training as well as 1,038 hours of unlabeled audio snippets for self-supervised…
This paper introduces a new framework for supervised sound source localization referred to as virtually-supervised learning. An acoustic shoe-box room simulator is used to generate a large number of binaural single-source audio scenes.…
The growing prevalence of speech deepfakes has raised serious concerns, particularly in real-world scenarios such as telephone fraud and identity theft. While many anti-spoofing systems have demonstrated promising performance on…