This paper proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed method, called ConvS2S-VC, has three key features. First, it uses a model with a fully…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,982 papers · 148 categories
Trend · papers per month
48 results for “speaker conversion”
Improved autoencoder for F0-consistent voice conversion.
problem Non-parallel many-to-many voice conversion with prosodic information leakage.
method Conditional autoencoder with information-constraining bottlenecks.
result Controlled F0 contour and improved speech quality.
Many-to-Many VTN improves voice conversion across multiple speakers.
problem Voice conversion across multiple speakers.
method Sequence-to-sequence learning framework with many-to-many VTN architecture.
result Improved sound quality and speaker similarity compared to baseline methods.
One-shot VC model converts voices without parallel data.
problem Limited VC applicability due to training data restriction.
method Disentangles speaker and content representations with instance normalization.
result Model converts voices from unseen speakers with high similarity.
Convolutional network converts speaker voices without text.
problem Speaker conversion without text-based methods.
method Fully convolutional wav-to-wav network with ASR pre-training.
result Successfully converts TTS robot's voice to narrated audiobook voices.
An audiovisual speaker conversion method is presented for simultaneously transforming the facial expressions and voice of a source speaker into those of a target speaker. Transforming the facial and acoustic features together makes it possible for the converted voice and facial expressions to be highly correlated and f…
The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methodseess.AS
We present the Voice Conversion Challenge 2018, designed as a follow up to the 2016 edition with the aim of providing a common framework for evaluating and comparing different state-of-the-art voice conversion (VC) systems. The objective of the challenge was to perform speaker conversion (i.e. transform the vocal ident…
FasterVoiceGrad speeds up VC by 6-7x with novel distillation.
problem Slow iterative sampling in diffusion-based VC models.
method Adversarial diffusion conversion distillation (ADCD) to create a faster one-step model.
result 6.6-6.9 and 1.8x faster on GPU and CPU, respectively.
Improved voice conversion with semi-supervised learning.
problem Voice conversion with limited parallel data.
method Amortized variational inference with parallel and non-parallel utterances.
result Semi-supervised training improves voice conversion performance.
We present a TTS neural network that is able to produce speech in multiple languages. The proposed network is able to transfer a voice, which was presented as a sample in a source language, into one of several target languages. Training is done without using matching or parallel data, i.e., without samples of the same …
Blow converts non-parallel raw audio voices efficiently.
problem Voice conversion with non-parallel data.
method Single-scale normalizing flow with hypernetwork conditioning.
result Blow outperforms existing flow-based architectures in voice conversion.
Constrained speaker linkingstat.ML
In this paper we study speaker linking (a.k.a.\ partitioning) given constraints of the distribution of speaker identities over speech recordings. Specifically, we show that the intractable partitioning problem becomes tractable when the constraints pre-partition the data in smaller cliques with non-overlapping speakers…
Voice conversion (VC) aims at conversion of speaker characteristic without altering content. Due to training data limitations and modeling imperfections, it is difficult to achieve believable speaker mimicry without introducing processing artifacts; performance assessment of VC, therefore, usually involves both speaker…
Proposes a new voice conversion model that preserves pitch patterns.
problem Preserving pitch patterns while changing speaker identity.
method Variational-autoencoder-based model with an auxiliary network.
result Ensures the conversion result correctly reflects specified F0/timbre information.
We propose a flexible framework for spectral conversion (SC) that facilitates training with unaligned corpora. Many SC frameworks require parallel corpora, phonetic alignments, or explicit frame-wise correspondence for learning conversion functions or for synthesizing a target spectrum with the aid of alignments. Howev…
The human auditory system is able to distinguish the vocal source of thousands of speakers, yet not much is known about what features the auditory system uses to do this. Fourier Transforms are capable of capturing the pitch and harmonic structure of the speaker but this alone proves insufficient at identifying speaker…
StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networkscs.SD
This paper proposes a method that allows non-parallel many-to-many voice conversion (VC) by using a variant of a generative adversarial network (GAN) called StarGAN. Our method, which we call StarGAN-VC, is noteworthy in that it (1) requires no parallel utterances, transcriptions, or time alignment procedures for speec…
NIST CTS Superset offers a large dataset for telephony speaker recognition.
problem Lack of a large-scale, uniform dataset for telephony speaker recognition.
method Compilation of speech segments from multiple corpora, including Greybeard, Switchboard, and Mixer series.
result Results on the NIST 2020 CTS Speaker Recognition Challenge serve as a reference baseline.
Recent speech technology research has seen a growing interest in using WaveNets as statistical vocoders, i.e., generating speech waveforms from acoustic features. These models have been shown to improve the generated speech quality over classical vocoders in many tasks, such as text-to-speech synthesis and voice conver…
WEEND uses a neural network to recognize speech and assign speakers to words.
problem End-to-end neural diarization without additional ASR and orchestration.
method Multi-task learning with an auxiliary network for ASR and speaker diarization.
result WEEND outperforms turn-based diarization and can handle 5-minute audio.
Neuro-symbolic system tackles conversational AI's need for natural, broad-ranging dialogue.
problem Understanding unstated presumptions in conversational AI commands.
method Neuro-symbolic theorem prover for multi-hop reasoning.
result Extracts multi-hop reasoning chains from natural language commands.
We investigated the training of a shared model for both text-to-speech (TTS) and voice conversion (VC) tasks. We propose using an extended model architecture of Tacotron, that is a multi-source sequence-to-sequence model with a dual attention mechanism as the shared model for both the TTS and VC tasks. This model can a…
FastVoiceGrad speeds up VC to one step, matching or surpassing quality.
problem Slow inference in multi-step diffusion-based VC.
method Adversarial Conditional Diffusion Distillation (ACDD) for one-step diffusion.
result One-shot VC with superior or comparable performance to multi-step methods.
In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers. Inspired by the recent success of deep neural networks (DNNs) in semantic inferencing, triplet loss-based architectures have been successfully used for this problem. However, existi…
Level assessment for foreign language students is necessary for putting them in the right level group, furthermore, interviewing students is a very time-consuming task, so we propose to automate the evaluation of speaker fluency level by implementing machine learning techniques. This work presents an audio processing s…
Inspired by recent work on neural network image generation which rely on backpropagation towards the network inputs, we present a proof-of-concept system for speech texture synthesis and voice conversion based on two mechanisms: approximate inversion of the representation learned by a speech recognition neural network,…
SuTaT creates dialogue summaries for tete-a-tetes without labeled data.
problem Lack of high-quality paired dialogue-summary data.
method Unsupervised model for tete-a-tetes, modeling customer and agent roles separately.
result SuTaT outperforms on automatic and human evaluations.
In this paper we describe the recent advancements made in the IBM i-vector speaker recognition system for conversational speech. In particular, we identify key techniques that contribute to significant improvements in performance of our system, and quantify their contributions. The techniques include: 1) a nearest-neig…
Standard probabilistic linear discriminant analysis (PLDA) for speaker recognition assumes that the sample's features (usually, i-vectors) are given by a sum of three terms: a term that depends on the speaker identity, a term that models the within-speaker variability and is assumed independent across samples, and a fi…
In some speaker recognition scenarios we find conversations recorded simultaneously over multiple channels. That is the case of the interviews in the NIST SRE dataset. To take advantage of that, we propose a modification of the PLDA model that considers two different inter-session variability terms. The first term is t…
A fast voice conversion method using diffusion models.
problem One-shot many-to-many voice conversion.
method Diffusion probabilistic modeling with Fast Maximum Likelihood Sampling Scheme.
result Superior quality compared to state-of-the-art approaches.
Enhances dialogue model with persona attributes using adversarial learning.
problem Improving dialogue models to better capture speaker identity and topic.
method Adversarial learning framework with a dual discriminator system.
result phredGAN outperforms persona Seq2Seq model in various datasets.
Solution for voice conversion with limited data using hierarchical seq2seq and attention models.
problem Voice conversion between speakers with limited parallel audio pairs.
method Hierarchical sequence to sequence model with attention-based decoder, trained on single speaker dataset.
result Improved voice conversion quality using mel spectrograms and wavenet vocoder.
Improved voice conversion model using single generator.
problem Challenges in non-parallel multi-domain voice conversion.
method Revised conditional methods in StarGAN-VC2, including new loss functions and network architectures.
result Significant improvement in speech quality and naturalness.
Integrating end-to-end neural and clustering-based diarization: Getting the best of both worldseess.AS
Hybrid diarization framework handles overlapped speech and long recordings.
problem Challenges in clustering-based and end-to-end neural diarization approaches.
method Proposes a hybrid framework combining clustering and end-to-end neural diarization.
result Significantly better performance on long recordings with overlapped speech.
We propose a nonparallel data-driven emotional speech conversion method. It enables the transfer of emotion-related characteristics of a speech signal while preserving the speaker's identity and linguistic content. Most existing approaches require parallel data and time alignment, which is not available in most real ap…
Enhances persona-based conversation model for multi-turn dialogue.
problem Improving persona-based conversation models for multi-turn dialogue.
method Introduced additional input modality into hredGAN to capture external attributes.
result Persona hredGAN () outperforms existing models in multi-turn dialogue corpora.
We present the recent advances along with an error analysis of the IBM speaker recognition system for conversational speech. Some of the key advancements that contribute to our system include: a nearest-neighbor discriminant analysis (NDA) approach (as opposed to LDA) for intersession variability compensation in the i-…
A new Multi-Stream VAE separates multiple sources in images and audio.
problem Learning disentangled representations in multi-stream data.
method Combines discrete and continuous latent spaces for source separation.
result Competitive performance in separating superimposed digits and sound sources.
Inspired by brain's modality fusion, this paper detects active speakers from audio and video.
problem Detecting active speakers in noisy environments.
method Inspired by brain's superior colliculus, combines audio and visual data through specialized neural networks and a novel fusion layer.
result Achieved results greatly surpassing initial expectations, confirming the effectiveness of the proposed method.
Memory-Augmented Recurrent Networks improve dialogue coherence by expanding conversation history storage.
problem Fixed-size vectors limit dialogue coherence; attention mechanisms are computationally expensive.
method Introduce Neural Turing Machines (NTMs) to provide flexible and permanent storage for dialogue history.
result Improved perplexity performance compared to existing baselines.
End-to-end voice conversion without vocoder.
problem Speech conversion without vocoder.
method Transformer network for raw spectrum conversion.
result Transformer model converts real voices efficiently.
This paper proposes a non-parallel many-to-many voice conversion (VC) method using a variant of the conditional variational autoencoder (VAE) called an auxiliary classifier VAE (ACVAE). The proposed method has three key features. First, it adopts fully convolutional architectures to construct the encoder and decoder ne…
MaskCycleGAN-VC improves voice conversion without parallel data.
problem Limited ability to convert mel-spectrogram data without parallel data.
method Integrates a novel auxiliary task called filling in frames (FIF) to learn time-frequency structures.
result MaskCycleGAN-VC outperforms existing methods with similar model size.
Proposes DNN-based speaker embedding correlated with subjective inter-speaker similarity for speech synthesis.
problem Inadequate speaker representation for open speakers not in training data.
method Two training algorithms using inter-speaker similarity matrices: similarity vector embedding and similarity matrix embedding.
result Proposed algorithms learn speaker embedding highly correlated with subjective inter-speaker similarity.
CycleGAN-VC2 improves voice conversion without parallel data.
problem Challenges in non-parallel voice conversion.
method Improved CycleGAN-VC with three techniques: two-step adversarial losses, 2-1-2D CNN generator, and PatchGAN discriminator.
result CycleGAN-VC2 significantly reduces the gap between converted and target speech.
When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies have shown that neural multi-speaker TTS model trained with a small amount data f…
Self-attentive network improves emotion recognition in conversations.
problem Emotion recognition in dyadic conversations using deep learning.
method Introduces a novel self-attention mechanism for capturing temporal dynamics without a decoder.
result Outperforms state-of-the-art alternatives on the IEMOCAP benchmark.