相关论文: A Holistic Cascade System, benchmark, and Human Ev…

This paper describes progress towards making a Neural Text-to-Speech (TTS) Frontend that works for many languages and can be easily extended to new languages. We take a Machine Translation (MT) inspired approach to constructing the…

Text-to-Speech (TTS) benchmarks often fail to capture how well models handle nuanced and semantically complex text. Building on $\textit{EmergentTTS}$, we introduce $\textit{EmergentTTS-Eval}$, a comprehensive benchmark covering six…

Generating expressive speech with rich and varied prosody continues to be a challenge for Text-to-Speech. Most efforts have focused on sophisticated neural architectures intended to better model the data distribution. Yet, in evaluations it…

Evaluation of Text to Speech (TTS) systems is challenging and resource-intensive. Subjective metrics such as Mean Opinion Score (MOS) are not easily comparable between works. Objective metrics are frequently used, but rarely validated…

Speech emotions play a crucial role in human-computer interaction, shaping engagement and context-aware communication. Despite recent advances in spoken dialogue systems, a holistic system for evaluating emotional reasoning is still…

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

Speech translation for low-resource languages remains fundamentally limited by the scarcity of high-quality, diverse parallel speech data, a challenge that is especially pronounced in African linguistic contexts. To address this, we…

This paper describes the cascaded multimodal speech translation systems developed by Imperial College London for the IWSLT 2019 evaluation campaign. The architecture consists of an automatic speech recognition (ASR) system followed by a…

Emotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity. Prior studies show that it is possible to disentangle emotional prosody using an encoder-decoder network…

We propose a novel causal prosody mediation framework for expressive text-to-speech (TTS) synthesis. Our approach augments the FastSpeech2 architecture with explicit emotion conditioning and introduces counterfactual training objectives to…

Incorporating longer context has been shown to benefit machine translation, but the inclusion of context in end-to-end speech translation (E2E-ST) remains under-studied. To bridge this gap, we introduce target language context in E2E-ST,…

We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. It follows fairseq's careful design for scalability and extensibility. We provide…

In this project, we aim to build a Text-to-Speech system able to produce speech with a controllable emotional expressiveness. We propose a methodology for solving this problem in three main steps. The first is the collection of emotional…

Expressive text-to-speech has shown improved performance in recent years. However, the style control of synthetic speech is often restricted to discrete emotion categories and requires training data recorded by the target speaker in the…

Five years after the first published proofs of concept, direct approaches to speech translation (ST) are now competing with traditional cascade solutions. In light of this steady progress, can we claim that the performance gap between the…

Speech emotion conversion is the task of modifying the perceived emotion of a speech utterance while preserving the lexical content and speaker identity. In this study, we cast the problem of emotion conversion as a spoken language…

Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesized speech of a target speaker's timbre. In most previous methods, the synthesized fine-grained prosody features often represent…

Speech classification tasks often require powerful language understanding models to grasp useful features, which becomes problematic when limited training data is available. To attain superior classification performance, we propose to…

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…

Simultaneous speech-to-text translation (SimulST) translates source-language speech into target-language text concurrently with the speaker's speech, ensuring low latency for better user comprehension. Despite its intended application to…