A new deep neural network improves short-speech recognition.
problem Improving speaker recognition for short-duration speech segments.
method Proposes UtterIdNet, a novel deep neural network architecture.
result Consistent and stable performance for short segments, especially sub-second durations.
Spoken language translation (SLT) has become very important in an increasingly globalized world. Machine translation (MT) for automatic speech recognition (ASR) systems is a major challenge of great interest. This research investigates that automatic sentence segmentation of speech that is important for enriching speec…
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).
Unified deep learning framework improves SV in noisy, reverberant, and long non-speech segments.
problem Robust speaker verification in adverse environments, especially short speech segments.
method Feature Pyramid Module (FPM)-based Multi-scale Aggregation (MSA), Self-adaptive Soft VAD (SAS-VAD), Masking-based Speech Enhancement (SE).
result The proposed method outperforms baseline systems in challenging conditions.
SwishNet improves speech, music, and noise classification and segmentation.
problem Speech, Music, and Noise classification/segmentation for audio processing.
method Proposes a fast and lightweight 1D CNN (SwishNet) for MFCC features, trained with knowledge distillation from ImageNet.
result Achieved high accuracy (>97% clip classification, >93% frame-wise segmentation) on MUSAN corpus.
Proposes a new model for better speech segmentation.
problem Improving speech segmentation accuracy.
method Integrates recurrent explicit duration variables into rSLDS and uses Pólya-gamma augmentation for inference.
result Demonstrates improved segmentation on various datasets.
Neural model detects phoneme boundaries from speech, outperforming baselines.
problem Phoneme boundary detection for speech processing applications.
method Learnable segmental features with a structured loss function.
result Model achieves state-of-the-art performance on TIMIT and Buckeye corpora.
Unsupervised speech recognition without labeled data using novel cost function and MAP refinement.
problem Training speech recognition systems without labeled data.
method Alternates between phoneme classifier learning and boundary refinement using Segmental Empirical Output Distribution Matching and MAP approach.
result Achieves phone error rate (PER) of 41.6% on TIMIT dataset.
Enhanced speech emotion recognition using nonlinear recurrence dynamics.
problem Improving speech emotion recognition accuracy.
method Phase space reconstruction, Recurrence Plot, Recurrence Quantification Analysis, statistical functionals, feature fusion, Bidirectional Recurrent Neural Network.
result State-of-the-art performance on IEMOCAP with up to 10.7% improvement in accuracy.
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.
We derive a convex optimization problem for the task of segmenting sequential data, which explicitly treats presence of outliers. We describe two algorithms for solving this problem, one exact and one a top-down novel approach, and we derive a consistency results for the case of two segments and no outliers. Robustness…
Improves TTS accuracy by correcting context-dependent units.
problem Improves text-to-speech accuracy through speaker adaptation.
method Statistical model predicting context-dependent phonetic unit classes and their mean error values.
result Corrected boundaries of units improve TTS accuracy compared to HMM segmentation.
An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as Variational Autoencoders (VAEs) have achieved tremendous success in modeling natur…
Dr.VOT measures both positive and negative VOTs accurately in natural speech.
problem Accurate measurement of VOT in natural speech.
method Deep-learning model based on RNNs for structured prediction.
result Dr.VOT improves over state-of-the-art performance on VOT estimation.
Segmental structure is a common pattern in many types of sequences such as phrases in human languages. In this paper, we present a probabilistic model for sequences via their segmentations. The probability of a segmented sequence is calculated as the product of the probabilities of all its segments, where each segment …
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%.
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.
SepIt improves speech separation for multiple speakers.
problem Improving speech separation for multiple speakers in single channel recordings.
method SepIt uses a deep neural network that iteratively improves estimates of different speakers based on mutual information.
result SepIt outperforms state-of-the-art methods for 2, 3, 5, and 10 speakers.
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.
Study improves radio show segmentation using audio embeddings.
problem Automated segmentation of radio shows.
method Created audio embeddings from multi-class classification tasks on different datasets, evaluated performance against text-only baseline.
result Audio embeddings from non-speech sound event classification significantly outperformed text-only baseline by 32.3% in F1-measure.
The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address robustness by studying domain invariant features, such that domain information become…
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.
Paper proposes a new framework for SAD using GANs.
problem Speech Activity Detection (SAD) in diverse conditions.
method Joint learning with GANs and temporal discriminator.
result Framework outperforms state-of-the-art SAD approaches.
New neural network design improves speech enhancement metrics.
problem Improving speech enhancement metrics in noisy conditions.
method Combination of convolutional and recurrent layers in U-net architecture.
result Proposed solution outperforms current state-of-the-art in SDR, SIR, and STOI metrics.
Study proposes a decision tree for more accurate depression recognition in speech.
problem Subjective bias in traditional depression diagnosis methods.
method A novel speech segment fusion method based on decision tree.
result The proposed decision tree model improves depression classification performance.
Speech enhancement model is used to map a noisy speech to a clean speech. In the training stage, an objective function is often adopted to optimize the model parameters. However, in most studies, there is an inconsistency between the model optimization criterion and the evaluation criterion on the enhanced speech. For …
The paper extends influence functions to sequence tagging tasks for better model interpretability.
problem Lack of interpretability methods for sequence tagging models.
method Define and compute influence of training instance segments on test segment predictions.
result The segment influence method tracks with true influence and identifies annotation errors.
End-to-end TTS framework uses hard alignment to improve accuracy.
problem End-to-end TTS systems struggle with accurate alignment between input text and output acoustic features.
method Proposes a constrained alignment scheme with hard monotonic alignments, marginalized during training.
result Improves alignment learning and prediction in end-to-end TTS systems.
Deep learning predicts mental disorders from audio and text samples.
problem Predicting mental disorders from speech samples.
method Multimodal deep learning structure using various pre-trained models for audio and text embeddings, transfer learning, and auxiliary corpora.
result Acceptable accuracy in predicting mental disorders through multimodal analysis.
Recent work on discriminative segmental models has shown that they can achieve competitive speech recognition performance, using features based on deep neural frame classifiers. However, segmental models can be more challenging to train than standard frame-based approaches. While some segmental models have been success…
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.
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.
This paper aims to address two issues existing in the current speech enhancement methods: 1) the difficulty of phase estimations; 2) a single objective function cannot consider multiple metrics simultaneously. To solve the first problem, we propose a novel convolutional neural network (CNN) model for complex spectrogra…
Investigates neural TTS systems for Japanese and English.
problem Improving neural TTS systems for high-quality speech synthesis.
method Comparative study of neural sequence-to-sequence TTS vs. DNN pipeline TTS, varying model architecture, parameter size, and language.
result A neural sequence-to-sequence TTS system requires sufficient model parameters and a powerful encoder for high-quality speech synthesis.
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…
End-to-end ASR error detection using audio-transcript entailment.
problem Detecting transcription errors in ASR systems to prevent error propagation.
method Proposes a novel end-to-end approach using audio-transcript entailment, with acoustic and linguistic encoders.
result Achieves CER of 26.2% on all transcription errors and 23% on medical errors specifically, improving by 12% and 15.4% respectively over a strong baseline.
The objective of change-point detection is to discover abrupt property changes lying behind time-series data. In this paper, we present a novel statistical change-point detection algorithm based on non-parametric divergence estimation between time-series samples from two retrospective segments. Our method uses the rela…
Neural network framework for language recognition considers sequence information and improves accuracy.
problem Challenging task of automatic language identification in noisy conditions.
method Proposes a neural network framework with bidirectional LSTM and attention modeling for relevance weighting.
result Significant improvements over conventional methods in noisy conditions and multi-speaker speech.
We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are discriminative for partition labels given in training data. Previous deep network …
Paper improves video feature learning for better downstream tasks.
problem Improving video feature learning for better performance on downstream tasks.
method Self-supervised learning approach using contrastive bidirectional transformer, extending BERT for real-valued feature vectors.
result Significantly improved performance on video classification, captioning, and segmentation tasks.
Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach named Houdini for gene…
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…
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…
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.
Self multi-head attention improves speaker recognition for long utterances.
problem Speaker recognition for long speech segments using Deep Learning.
method Convolutional Neural Network (CNN) for short-term features, self multi-head attention for long-term embeddings.
result Self multi-head attention outperforms other pooling methods by 18% relative EER on VoxCeleb1 dataset.