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

Speech style editing refers to modifying the stylistic properties of speech while preserving its linguistic content and speaker identity. However, most existing approaches depend on explicit labels or reference audio, which limits both…

Speaker verification (SV) provides billions of voice-enabled devices with access control, and ensures the security of voice-driven technologies. As a type of biometrics, it is necessary that SV is unbiased, with consistent and reliable…

Goal: Numerous studies had successfully differentiated normal and abnormal voice samples. Nevertheless, further classification had rarely been attempted. This study proposes a novel approach, using continuous Mandarin speech instead of a…

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…

Speech-to-Speech (S2S) Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling end-to-end spoken dialogue systems. However, evaluating these models remains a fundamental challenge. We propose…

MOS (Mean Opinion Score) is a subjective method used for the evaluation of a system's quality. Telecommunications (for voice and video), and speech synthesis systems (for generated speech) are a few of the many applications of the method.…

While many recent any-to-any voice conversion models succeed in transferring some target speech's style information to the converted speech, they still lack the ability to faithfully reproduce the speaking style of the target speaker. In…

Code-switching (CS) is the alternating use of two or more languages within a conversation or utterance, often influenced by social context and speaker identity. This linguistic phenomenon poses challenges for Automatic Speech Recognition…

This paper introduces a high-quality open-source speech synthesis dataset for Kazakh, a low-resource language spoken by over 13 million people worldwide. The dataset consists of about 93 hours of transcribed audio recordings spoken by two…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Synthetic data has become an important tool in the fine-tuning of language models to follow instructions and solve complex problems. Nevertheless, the majority of open data to date is often lacking multi-turn data and collected on closed…

Advancements in spoken language processing have driven the development of spoken language models (SLMs), designed to achieve universal audio understanding by jointly learning text and audio representations for a wide range of tasks.…

It is relatively easy to mine a large parallel corpus for any machine learning task, such as speech-to-text or speech-to-speech translation. Although these mined corpora are large in volume, their quality is questionable. This work shows…

Models are increasing in size and complexity in the hunt for SOTA. But what if those 2\% increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, faster model outweigh those slight…

Recent advances in text-to-speech (TTS) have been driven by large, multi-domain speech corpora, yet the expressive potential of audiobook data remains underexamined. We argue that human-narrated audiobooks, particularly fictional works,…

The DISC project aims to (a) build an in-depth understanding of the state-of-the-art in spoken language dialogue systems (SLDSs) and components development and evaluation with the purpose of (b) developing a first best practice methodology…

For real-life applications, it is crucial that end-to-end spoken language translation models perform well on continuous audio, without relying on human-supplied segmentation. For online spoken language translation, where models need to…

Although discrete speech tokens have exhibited strong potential for language model-based speech generation, their high bitrates and redundant timbre information restrict the development of such models. In this work, we propose LSCodec, a…

Many commercial and forensic applications of speech demand the extraction of information about the speaker characteristics, which falls into the broad category of speaker profiling. The speaker characteristics needed for profiling include…

Sequence-to-Sequence Text-to-Speech architectures that directly generate low level acoustic features from phonetic sequences are known to produce natural and expressive speech when provided with adequate amounts of training data. Such…