Related papers: Any-to-One Sequence-to-Sequence Voice Conversion u…

With the development of automatic speech recognition (ASR) and text-to-speech (TTS) technology, high-quality voice conversion (VC) can be achieved by extracting source content information and target speaker information to reconstruct…

Voice conversion (VC) refers to transforming the speaker characteristics of an utterance without altering its linguistic contents. Many works on voice conversion require to have parallel training data that is highly expensive to acquire.…

Cross-lingual voice conversion (VC) is a task that aims to synthesize target voices with the same content while source and target speakers speak in different languages. Its challenge lies in the fact that the source and target data are…

This paper presents a simple end-to-end model for speech recognition, combining a convolutional network based acoustic model and a graph decoding. It is trained to output letters, with transcribed speech, without the need for force…

We propose PolyVoice, a language model-based framework for speech-to-speech translation (S2ST) system. Our framework consists of two language models: a translation language model and a speech synthesis language model. We use discretized…

Whispered speech lacks vocal-fold excitation, making intelligible conversion challenging. We propose WhisperVC, a three-stage framework for low-resource whisper-to-normal (W2N) conversion that decouples cross-domain alignment from speech…

Attention-based sequence-to-sequence (seq2seq) speech synthesis has achieved extraordinary performance. But a studio-quality corpus with manual transcription is necessary to train such seq2seq systems. In this paper, we propose an approach…

Controllable human voice generation, particularly for expressive domains like singing, remains a significant challenge. This paper introduces Vevo2, a unified framework for controllable speech and singing voice generation. To tackle issues…

Expressive voice conversion (VC) conducts speaker identity conversion for emotional speakers by jointly converting speaker identity and emotional style. Emotional style modeling for arbitrary speakers in expressive VC has not been…

We present a unified system to realize one-shot voice conversion (VC) on the pitch, rhythm, and speaker attributes. Existing works generally ignore the correlation between prosody and language content, leading to the degradation of…

Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio. However, current methods can only reenact a special person once the model is trained or need extra operations such…

Voice conversion is a task of synthesizing an utterance with target speaker's voice while maintaining linguistic information of the source utterance. While a speaker can produce varying utterances from a single script with different…

Sequence-to-sequence (seq2seq) voice conversion (VC) models have greater potential in converting electrolaryngeal (EL) speech to normal speech (EL2SP) compared to conventional VC models. However, EL2SP based on seq2seq VC requires a…

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new direction in speech research. The approach benefits by performing model training without using lexicon and alignments. However, this poses a new problem of…

In this paper, we describe our speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022). Firstly, we build an any-to-many voice conversion (VC) system to convert source speech with arbitrary language…

We present Translatotron 2, a neural direct speech-to-speech translation model that can be trained end-to-end. Translatotron 2 consists of a speech encoder, a linguistic decoder, an acoustic synthesizer, and a single attention module that…

We present OpenSeq2Seq - a TensorFlow-based toolkit for training sequence-to-sequence models that features distributed and mixed-precision training. Benchmarks on machine translation and speech recognition tasks show that models built using…

In this work, we introduce Vid2Seq, a multi-modal single-stage dense event captioning model pretrained on narrated videos which are readily-available at scale. The Vid2Seq architecture augments a language model with special time tokens,…

The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods rely heavily on annotated data, and struggle with effectively disentangling timbre…

Zero-shot voice conversion (VC) aims to transform source speech into arbitrary unseen target voice while keeping the linguistic content unchanged. Recent VC methods have made significant progress, but semantic losses in the decoupling…