8 accepted papers
Emotion recognition in speech presents a complex multimodal challenge, requiring comprehension of both linguistic content and vocal expressivity, particularly prosodic features such as fundamental frequency, intensity, and temporal dynamics. Although large language models (LLMs) have shown promise i…
Large language models (LLMs) have revolutionized natural language processing (NLP) with impressive performance across various text-based tasks. However, the extension of text-dominant LLMs to with speech generation tasks remains underexplored. In this work, we introduce a text-to-speech (TTS) system…
A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer. Recently, methods that leverage self-supervised audio representations such as HuBERT and Wav2Vec 2.0 have helped further the state-of-the-art. Though these methods produce mor…
Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker’s accent. For native speakers, understanding or speaking a new accent is likewise a difficult task. An accent conversion system that changes a speaker’s accent b…
Low bitrate speech codecs have become an area of intense research. Traditional speech codecs, which use signal processing methods to encode and decode speech, often suffer from quality issues at low bitrates. A neural speech codec, which uses a deep neural network in the compression pipeline, can he…
State of the art text-to-speech (TTS) models can generate high fidelity monolingual speech, but it is still challenging to synthesize multilingual speech from the same speaker. One major hurdle is for training data. It’s hard to find speakers who have native proficiency in several languages. One way…
Neural vocoders, used for converting the spectral representations of an audio signal to the waveforms, are a commonly used component in speech synthesis pipelines. It focuses on synthesizing waveforms from low-dimensional representation, such as Mel-Spectrograms. In recent years, different approache…
Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio. High-quality spectrum models usually incorporate the encoder-decoder architecture with self-attention…