This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a -vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “speaker similarity”
More and more neural network approaches have achieved considerable improvement upon submodules of speaker diarization system, including speaker change detection and segment-wise speaker embedding extraction. Still, in the clustering stage, traditional algorithms like probabilistic linear discriminant analysis (PLDA) ar…
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedd…
Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant performance gap between recognizing speakers in the training set and unseen speakers. …
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…
In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with similar approaches, we do not extract the embedding of an utterance from the mean redu…
LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify the speaker, which results in a critical mismatch between testing and training. T…
BOFFIN TTS optimizes hyper-parameters for new speaker adaptation.
problem Fine-tuning a pre-trained TTS model for a new speaker with limited data.
method Bayesian optimization to efficiently find optimal hyper-parameters.
result Average 30% improvement in speaker similarity over standard techniques.
A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown promising results. The extracted frame-level (DNN bottleneck, posterior or d-vector) …
We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of training is not to produce a neural network with fixed weights, which is then deplo…
Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-target scenario in which a single model is trained to convert the input voice to many different speakers. However, such model suffers from the limitation that it can only convert the voice to the speakers in the training data, …
Speaker clustering is the task of differentiating speakers in a recording. In a way, the aim is to answer "who spoke when" in audio recordings. A common method used in industry is feature extraction directly from the recording thanks to MFCC features, and by using well-known techniques such as Gaussian Mixture Models (…
We propose an algorithm to separate simultaneously speaking persons from each other, the "cocktail party problem", using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is descriptive of independent speakers. Such a vector space can embed empirically determi…
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.
We propose a novel adversarial speaker adaptation (ASA) scheme, in which adversarial learning is applied to regularize the distribution of deep hidden features in a speaker-dependent (SD) deep neural network (DNN) acoustic model to be close to that of a fixed speaker-independent (SI) DNN acoustic model during adaptatio…
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.
Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to voco…
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…
DKULENOVO team improves speech diarization by 27.5% and 31.7% in DIHARD II.
problem Challenges in speech diarization, especially in distinguishing overlapping speakers.
method Used a combination of VAD, speaker embedding extraction, similarity scoring, clustering, and resegmentation techniques.
result Achieved 18.84% DER in Track1 and 27.90% DER in Track2, reducing baseline DERs by 27.5% and 31.7% respectively.
Improved LID for multilingual speakers using context-aware models.
problem Low accuracy for languages spoken by multilingual speakers, especially with accented speech.
method Coarser-grained acoustic model and integration with interaction context signals.
result Average 97% accuracy across all language combinations, 60% improvement in worst-case accuracy.
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…
Deep learning is still not a very common tool in speaker verification field. We study deep convolutional neural network performance in the text-prompted speaker verification task. The prompted passphrase is segmented into word states - i.e. digits -to test each digit utterance separately. We train a single high-level f…
NIST's CTS Challenge evaluates speaker recognition using telephony data.
problem Improving speaker recognition accuracy using telephony data.
method Large-scale neural network architectures, extensive data augmentation, proprietary data, and fine-tuning.
result Remarkable improvements in speaker recognition performance.
Study compares metric learning loss functions for speaker verification.
problem Comparing metric learning loss functions for end-to-end speaker verification.
method Cross entropy loss, cosine loss, angular margin loss, center loss, contrastive loss, triplet loss.
result Additive angular margin loss outperforms other loss functions.
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) …
A Speaker Verification Backend for Improved Calibration Performance across Varying Conditionseess.AS
Simplified speaker verification backend improves calibration across varying conditions.
problem Improving calibration performance in speaker verification across different conditions.
method Jointly trained parameters and simplified calibration vectors.
result Simplified method achieves similar performance to previous method but is faster and easier to implement.
The paper proposes deep normalization to improve speaker recognition performance.
problem Non-Gaussian and non-homogeneous distributions of deep speaker vectors negatively impact speaker recognition.
method Proposes a deep normalization approach based on a novel discriminative normalization flow (DNF) model.
result DNF-based normalization delivers substantial performance gains and strong generalization capability.
Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments…
Speaker diarization with session-level speaker embedding refinement using graph neural networkseess.AS
Graph neural networks refine speaker embeddings for better session-level diarization.
problem Local speaker distinction in meeting sessions using deep embeddings.
method Graph Neural Networks (GNNs) refine speaker embeddings using session-level structural information.
result Spectral clustering on refined embeddings outperforms original embeddings significantly.
Improved neural speaker embeddings enhance ASR performance.
problem Few studies have explored neural speaker embeddings for ASR.
method Integrating improved neural speaker embeddings into a conformer-based hybrid HMM ASR system.
result Improved neural embeddings achieve on-par performance with i-vectors.
Paper improves speaker verification with federated learning and differential privacy.
problem Improving speaker verification accuracy using private data.
method Combining federated learning and differential privacy to train an auxiliary model that predicts vocal characteristics.
result 6% relative improvement in equal error rate over a baseline system.
An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Networkeess.AS
This paper presents an end-to-end text-independent speaker verification framework by jointly considering the speaker embedding (SE) network and automatic speech recognition (ASR) network. The SE network learns to output an embedding vector which distinguishes the speaker characteristics of the input utterance, while th…
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions. This is sometimes called "unsupervised speaker adaptation". More specifically, we…
Paper explores using EEG for better speaker identification, even in noisy environments.
problem Speaker identification performance degrades in background noise.
method Uses EEG signals to enhance speaker identification systems, comparing with acoustic features.
result Speaker identification system using only EEG features outperforms one using only acoustic features in high background noise.
New models extrapolate false alarms in ASV without new data.
problem Reliable extrapolation of false alarm rates in ASV without new speaker data.
method Generative models in ASV score space for arbitrary systems.
result Models accurately extrapolate false alarm rates for large speaker populations.
Improves speaker verification for variable-duration utterances using a feature pyramid module.
problem Improving robustness for variable-duration utterances in speaker verification.
method Integrates a feature pyramid module into multi-scale aggregation to enhance speaker-discriminative information from multiple layers.
result Improves performance for both short and long utterances compared to state-of-the-art approaches.
The social media revolution has produced a plethora of web services to which users can easily upload and share multimedia documents. Despite the popularity and convenience of such services, the sharing of such inherently personal data, including speech data, raises obvious security and privacy concerns. In particular, …
New method separates multiple voices in mixed audio.
problem Separating multiple simultaneous speakers in audio.
method Gated neural networks trained at multiple steps, selecting actual number of speakers.
result Outperforms current state of the art for more than two speakers.
Improved multi-user VoiceFilter-Lite model for speech recognition.
problem Limited performance of multi-user VoiceFilter-Lite models.
method Dual learning rate schedule and FiLM for feature conditioning.
result Closed the performance gap between multi-user and single-user VoiceFilter-Lite models.
Improved far-field speaker verification for short utterances in noisy conditions.
problem Challenges in speaker verification on short utterances in uncontrolled noisy environments.
method Used deep neural network architectures (TDNN and ResNet) and experimented with various embedding extractors and training procedures.
result ResNet architectures outperform x-vector approach in speaker verification quality for both long and short utterances.
Most neural-network based speaker-adaptive acoustic models for speech synthesis can be categorized into either layer-based or input-code approaches. Although both approaches have their own pros and cons, most existing works on speaker adaptation focus on improving one or the other. In this paper, after we first systema…
Bayesian approach improves speech recognition with limited speaker data.
problem Reduces mismatch between training and evaluation data due to speaker differences.
method Bayesian learning for DNN adaptation models with limited speaker data.
result Bayesian adaptation consistently outperforms deterministic methods, reducing word error rates up to 1.4%.
This paper explores two techniques to improve the performance of text-dependent speaker verification systems based on deep neural networks. Firstly, we propose a general alignment mechanism to keep the temporal structure of each phrase and obtain a supervector with the speaker and phrase information, since both are rel…
The VoxCeleb Speaker Recognition Challenge 2019 aimed to assess how well current speaker recognition technology is able to identify speakers in unconstrained or `in the wild' data. It consisted of: (i) a publicly available speaker recognition dataset from YouTube videos together with ground truth annotation and standar…
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.
Study shows emotion affects speaker recognition and vice versa.
problem Dependencies between emotion and speaker recognition.
method Transfer learning and fine-tuning for emotion classification.
result Fine-tuning improves emotion recognition performance by 30.40% on IEMOCAP, 7.99% on MSP-Podcast, and 8.61% on Crema-D.
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…
In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN). Given extracted speaker-discriminative embeddings (a.k.a. d-vectors) from input utterances, each individual speaker is modeled by a parameter-sharing RNN, while the RNN state…