Improved speech segment clustering using FTDTW.
problem Clustering speech segments of varying lengths and features.
method Feature Trajectory Dynamic Time Warping (FTDTW) for pairwise alignment of feature trajectories.
result Consistent and statistically significant improvements in cluster quality (F-measure and NMI).
Improves speech separation by integrating time and frequency domains.
problem Speech separation using deep learning techniques.
method Proposes a framework that combines time and frequency domain features, using an embedding network and clustering.
result Obtained state-of-the-art results on WSJ0-2mix dataset.
Improved space management in iterative clustering reduces subset growth without sacrificing performance.
problem Iterative re-clustering of speech segments can lead to unchecked subset growth, compromising performance.
method Integration of a space management strategy into the iterative process of hierarchical clustering.
result No loss in performance in terms of F-measure while guaranteeing space complexity.
Wavesplit separates speech from mixtures using clustering.
problem Permutation problem in speech separation.
method End-to-end system infers speaker representations and estimates signals.
result Robust separation of long recordings, new benchmarks set.
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.
Probabilistic embeddings improve speaker diarization accuracy.
problem Improving speaker diarization accuracy using embeddings.
method Extracting x-vectors and precision matrices from speech segments, interfacing with PLDA model, applying agglomerative clustering, joint training of PLDA and extractor.
result Joint training of PLDA and probabilistic x-vector extractor yields accuracy gains.
Clustered attention improves transformer efficiency for large sequences.
problem Quadratic complexity of transformer attention matrix for large sequences.
method Group queries into clusters, compute attention only for centroids, and use centroids to approximate key/query dot products.
result Linear complexity with respect to sequence length for a fixed number of clusters.
Paper proposes LSTM for speaker similarity measurement and improves diarization accuracy.
problem Improving speaker diarization accuracy using neural networks.
method Uses Bi-LSTM for similarity measurement and spectral clustering for clustering.
result Significantly outperforms state-of-the-art methods with diarization error rate of 6.63%.
X-DC improves speech separation by making DNNs more interpretable.
problem Black-box nature of DNNs in speech separation tasks.
method Introduces X-DC, a DNN architecture that interprets as spectrogram template fitting followed by Wiener filtering.
result X-DC achieves comparable speech separation performance to DC but with enhanced interpretability.
End-to-end speech recognition system trained on GPUs and CPUs.
problem Building state-of-the-art speech recognition systems.
method Utilizes CPUs and GPUs for training, data augmentation, and neural network updates. Uses vocal tract length perturbation and acoustic simulator for data augmentation. Employed Horovod allreduce for training.
result Achieved 7.92% WER on proprietary English Bixby open domain test set using a Bidirectional Full Attention (BFA) model.
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.
Introspects convolutional speech recognition models using Gradient-adjusted Neuron Activation Profiles.
problem Lack of interpretability in deep learning ASR models.
method Gradient-adjusted Neuron Activation Profiles (GradNAPs) for feature and representation visualization.
result Gains insight into how data is processed in convolutional ASR models.
With rapidly increasing data, clustering algorithms are important tools for data analytics in modern research. They have been successfully applied to a wide range of domains; for instance, bioinformatics, speech recognition, and financial analysis. Formally speaking, given a set of data instances, a clustering algorith…
Deep clustering is a recently introduced deep learning architecture that uses discriminatively trained embeddings as the basis for clustering. It was recently applied to spectrogram segmentation, resulting in impressive results on speaker-independent multi-speaker separation. In this paper we extend the baseline system…
We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each 1≤k≤kmax, a distribution over the individual cluster assignm…
Unsupervised model generates distinct intonation codes for speech synthesis.
problem Lack of understanding of what prosodic variations are controlled in speech synthesis.
method Phrase-level variational autoencoder with multi-modal prior, using mode centres as intonation codes.
result Generated intonation codes are perceptually distinct and carry various affect-related styles.
Improved topic modeling captures temporal relationships in speech.
problem Lack of temporal information in LDA for speech analysis.
method Temporal Markov chain extension to LDA for acoustic unit discovery.
result Improved phone segmentation results compared to base LDA.
GCML preserves geometric structure in manifold clustering for diverse data types.
problem Loss functions in manifold clustering can corrupt latent space structure.
method GCML framework with isometric and ranking losses for geometric structure preservation.
result GCML outperforms other methods in latent space structure preservation and performance metrics.
Deep clustering is the first method to handle general audio separation scenarios with multiple sources of the same type and an arbitrary number of sources, performing impressively in speaker-independent speech separation tasks. However, little is known about its effectiveness in other challenging situations such as mus…
We perform a large-scale analysis of language diatopic variation using geotagged microblogging datasets. By collecting all Twitter messages written in Spanish over more than two years, we build a corpus from which a carefully selected list of concepts allows us to characterize Spanish varieties on a global scale. A clu…
Deep learning improves community detection in graph datasets.
problem Community detection in graph datasets using deep learning.
method Proposes a deep learning approach using Gumbel Softmax for clustering graph nodes.
result The new approach significantly outperforms traditional clustering methods.
ADPSGD enables faster ASR training with larger batch sizes.
problem Efficient distributed deep learning for ASR with large batch sizes.
method Asynchronous Decentralized Parallel Stochastic Gradient Descent (ADPSGD) and Hierarchical-ADPSGD (H-ADPSGD).
result ADPSGD can converge with a 3X larger batch size than SSGD, enabling faster training.
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…
End-to-end speech recognition using EEG without speech input.
problem Speech recognition without direct speech input.
method Implemented attention model and CTC-based ASR systems for EEG signals; fused EEG with noisy speech features.
result Demonstrated end-to-end speech recognition using EEG signals.
Paper shows EEG can improve ASR in noisy speech.
problem ASR performance drops in noisy conditions.
method Used EEG to train ASR models and improve performance.
result ASR accuracy improved with EEG features and distillation.
Paper shows continuous speech recognition with EEG features, no speech input.
problem Continuous speech recognition with limited vocabulary and noisy/no speech input.
method Connectionist temporal classification (CTC) model, EEG features, new deep learning architecture.
result Continuous speech recognition achieved on limited vocabulary with noisy/no speech input.
This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and para-linguistic information, typical statistical speech synthesis pr…
Compact SE models are created with PP and PQ techniques, reducing size by 10.03%.
problem Balancing denoising performance and computational cost in SE models.
method Parameter pruning and quantization techniques integrated for compactness.
result 10.03% reduction in model size with minor performance losses.
RUSLAN is a large Russian speech corpus for text-to-speech.
problem Lack of high-quality annotated Russian speech data for text-to-speech.
method Developed a large annotated Russian speech corpus and trained a neural network for text-to-speech synthesis.
result Synthesized speech quality evaluated with MOS scores: 4.05 for naturalness, 3.78 for intelligibility.
AeGAN improves speech clarity in noisy environments.
problem Improving speech recognition in crowded noisy environments.
method Generative adversarial networks (GAN) with a novel architecture.
result The proposed framework outperforms traditional and learning-based methods.
Detects AI-synthesized speech using cepstral and bispectral analysis.
problem Validating the authenticity of speech from AI-generated content.
method Integrates cepstral and bispectral analysis for distinguishing human from AI-synthesized speech.
result Higher-order statistics show less correlation for human speech compared to AI-synthesis, and cepstral analysis reveals unique power components.
Improved visual speech synthesis using adapted ASR acoustic models.
problem Lack of synchronized audio, video, and depth data for speaker-independent speech-driven visual speech synthesis.
method Adapted an ASR acoustic model trained on audio-only data to the visual speech synthesis domain.
result Viewers significantly prefer animations generated from the adapted ASR acoustic model.
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervis…
WaveCycleGAN2 improves speech synthesis quality by reducing aliasing.
problem Human ear can still distinguish synthesized speech from natural speech.
method WaveCycleGAN2 uses generators without down/up-sampling modules and combines discriminators from waveform and acoustic parameter domains.
result WaveCycleGAN2 achieves high-quality speech synthesis with comparable mean opinion scores to natural speech.
AudioPaLM combines text and speech models to improve speech processing and translation.
problem Improving speech understanding and generation models.
method Unified multimodal architecture combining text and speech models.
result AudioPaLM significantly outperforms existing speech translation systems.
Enhances spoken speech quality using EEG signals.
problem Improves speech clarity in noisy environments.
method Generative adversarial network (GAN), gated recurrent unit (GRU), temporal convolutional network (TCN) regression models.
result Significant improvement in speech enhancement quality compared to traditional methods.
Improved speech enhancement using diffusion models with MSE loss.
problem Efficient incorporation of noisy speech in generative speech enhancement.
method Augmented diffusion-based generative model with a MSE loss for enhanced speech.
result Proposed method improves speech enhancement performance compared to original diffusion model.
This work disentangles speech and non-speech components from found data.
problem Building robust acoustic models from found data with non-standard variations.
method Latent Stochastic Models and Multinode Latent Space Variational Autoencoders (VAE).
result Speech and music can be separated in the latent space of a VAE, independent of the language.
Continuous speech recognition from brain activity without vocalization.
problem Recognizing silent speech from EEG signals.
method Implemented a CTC ASR model using EEG signals.
result Demonstrated feasibility of EEG for continuous silent speech recognition.
Speech emotion recognition system using features and text.
problem Improving accuracy in emotion recognition from speech.
method Used speech features (Spectrogram, MFCC) and text, trained Deep Neural Networks.
result Combined MFCC-Text CNN model achieved highest accuracy.
AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
problem Improving AVSR performance with labeled and unlabeled data.
method Semi-supervised method using continuous pseudo-labels generated by the same AVSR model.
result Significant improvements in VSR performance on LRS3 dataset.
Enhanced text-to-speech synthesizes expressive speech from a single example.
problem Creating a new expressive speech style from a single example of speech.
method Combines VAE and Normalizing Flows to improve disentanglement and naturalness.
result Reduces KL-divergence by 22% and improves perceptual metrics.
Diffusion models enhance speech without supervision.
problem Challenges in generalizing supervised speech enhancement methods to unseen conditions.
method Unsupervised speech enhancement using diffusion-based generative models.
result Demonstrates promising results compared to supervised and unsupervised baselines.
Improved speech recognition using EEG and video.
problem Enhancing continuous speech recognition systems.
method Implemented a CTC-based ASR model using EEG features.
result EEG features improve continuous visual speech recognition.
Speech synthesis from EEG features using RNN.
problem Speech synthesis from EEG data.
method Recurrent Neural Network (RNN) regression model to predict acoustic features from EEG features.
result Feasibility of synthesizing speech directly from EEG features demonstrated.
Survey on DNNs for speech processing, focusing on limited data challenges.
problem Challenges in training DNNs for speech tasks with limited data.
method Overview of techniques for few-shot speech processing.
result Promising few-shot techniques for speech processing.
Speech enhancement improved by adapting to unknown speakers without auxiliary signals.
problem Improving speech enhancement accuracy for unknown speakers.
method Adopting multi-task learning for speech enhancement and speaker identification, using multi-head self-attention.
result Achieved state-of-the-art performance and improved subjective quality.
New speech recognition method uses hypergraphs for better label prediction.
problem Missed information in pairwise relationships between speech samples.
method Hypergraph Laplacian based semi-supervised learning methods applied to speech recognition.
result Sensitivity performance measures of hypergraph methods are better than state-of-the-art methods.