Related papers: Evaluating Objective Speech Quality Metrics for Ne…
Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in…
Large Language Models (LLMs) have significantly advanced audio processing by leveraging audio codecs to discretize audio into tokens, enabling the application of language modeling techniques to speech data. However, existing audio codecs…
The neural codec model reduces speech data transmission delay and serves as the foundational tokenizer for speech language models (speech LMs). Preserving emotional information in codecs is crucial for effective communication and context…
Computer voice is experiencing a renaissance through the growing popularity of voice-based interfaces, agents, and environments. Yet, how to measure the user experience (UX) of voice-based systems remains an open and urgent question,…
Predicting audio quality in voice synthesis and conversion systems is a critical yet challenging task, especially when traditional methods like Mean Opinion Scores (MOS) are cumbersome to collect at scale. This paper addresses the gap in…
Speech intelligibility assessment is essential for evaluating neural speech codecs, yet most evaluation efforts focus on overall quality rather than intelligibility. Only a few publicly available tools exist for conducting standardized…
Neural codecs have become crucial to recent speech and audio generation research. In addition to signal compression capabilities, discrete codecs have also been found to enhance downstream training efficiency and compatibility with…
Despite its crucial role in research experiments, code correctness is often presumed only on the basis of the perceived quality of results. This assumption comes with the risk of erroneous outcomes and potentially misleading findings. To…
Neural audio codecs (NACs), which use neural networks to generate compact audio representations, have garnered interest for their applicability to many downstream tasks -- especially quantized codecs due to their compatibility with large…
Evaluating state-of-the-art speech systems necessitates scalable and sensitive evaluation methods to detect subtle but unacceptable artifacts. Standard MUSHRA is sensitive but lacks scalability, while ACR scales well but loses sensitivity…
Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) \etc., which can be challenging to cover using one small model designed for a single task. In…
We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully…
The INTERSPEECH 2020 Deep Noise Suppression Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical…
Neural codecs, comprising an encoder, quantizer, and decoder, enable signal transmission at exceptionally low bitrates. Training these systems requires techniques like the straight-through estimator, soft-to-hard annealing, or statistical…
There is a considerable interest in developing algorithms that can predict audio quality of perceptually coded signals to avoid the cost of extensive listening tests during development time. While many established algorithms for predicting…
Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and…
Speech enhancement techniques improve the quality or the intelligibility of an audio signal by removing unwanted noise. It is used as preprocessing in numerous applications such as speech recognition, hearing aids, broadcasting and…
Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model:…
Speech embeddings are fixed-size acoustic representations of variable-length speech sequences. They are increasingly used for a variety of tasks ranging from information retrieval to unsupervised term discovery and speech segmentation.…
Audio Question Answering (AQA) is a key task for evaluating Audio-Language Models (ALMs), yet assessing open-ended responses remains challenging. Existing metrics used for AQA such as BLEU, METEOR and BERTScore, mostly adapted from NLP and…