End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal through systematic experimentation that although LSLMs lose some text input performance after speech-text alignment training, the performance gap between speech and text inputs is more pronounced, which we refer to as the modality gap. To understand this gap, we analyze both coarse- and fine-grained text and speech representations. At the coarse-grained level, representations of speech and text in deeper layers are found to be increasingly aligned in direction (cosine similarity), while concurrently diverging in magnitude (Euclidean distance). We further find that representation similarity is strongly correlated with the modality gap. At the fine-grained level, a spontaneous token-level alignment pattern between text and speech representations is observed. Based on this, we introduce the Alignment Path Score to quantify token-level alignment quality, which exhibits stronger correlation with the modality gap. Building on these insights, we design targeted interventions on critical tokens through angle projection and length normalization. These strategies demonstrate the potential to improve correctness for speech inputs. Our study provides the first systematic empirical analysis of the modality gap and alignment mechanisms in LSLMs, offering both theoretical and methodological guidance for future optimization.

Despite recent advances in end-to-end speech recognition methods, the output tends to be biased to the training data's vocabulary, resulting in inaccurate recognition of proper nouns and other unknown terms. To address this issue, we propose a method to improve recognition accuracy of such rare words in CTC-based models without additional training or text-to-speech systems. Specifically, keyword spotting is performed using acoustic features of intermediate layers during inference, and a bias is applied to the subsequent layers of the acoustic model for detected keywords. For keyword detection, we adopt a wild-card CTC that is both fast and tolerant of ambiguous matches, allowing flexible handling of words that are difficult to match strictly. Since this method does not require retraining of existing models, it can be easily applied to even large-scale models. In experiments on Japanese speech recognition, the proposed method achieved a 29% improvement in the F1 score for unknown words.

Temporal alignment of sequences is a fundamental challenge in many applications, such as computer vision and bioinformatics, where local time shifting needs to be accounted for. Misalignment can lead to poor model generalization, especially in high-dimensional sequences. Existing methods often struggle with optimization when dealing with high-dimensional sparse data, falling into poor alignments. Feature selection is frequently used to enhance model performance for sparse data. However, a fixed set of selected features would not generally work for dynamically changing sequences and would need to be modified based on the state of the sequence. Therefore, modifying the selected feature based on contextual input would result in better alignment. Our suggested method, Conditional Deep Canonical Temporal Time Warping (CDCTW), is designed for temporal alignment in sparse temporal data to address these challenges. CDCTW enhances alignment accuracy for high dimensional time-dependent views be performing dynamic time warping on data embedded in maximally correlated subspace which handles sparsity with novel feature selection method. We validate the effectiveness of CDCTW through extensive experiments on various datasets, demonstrating superior performance over previous techniques.

Multi-talker speech recognition (MTASR) faces unique challenges in disentangling and transcribing overlapping speech. To address these challenges, this paper investigates the role of Connectionist Temporal Classification (CTC) in speaker disentanglement when incorporated with Serialized Output Training (SOT) for MTASR. Our visualization reveals that CTC guides the encoder to represent different speakers in distinct temporal regions of acoustic embeddings. Leveraging this insight, we propose a novel Speaker-Aware CTC (SACTC) training objective, based on the Bayes risk CTC framework. SACTC is a tailored CTC variant for multi-talker scenarios, it explicitly models speaker disentanglement by constraining the encoder to represent different speakers' tokens at specific time frames. When integrated with SOT, the SOT-SACTC model consistently outperforms standard SOT-CTC across various degrees of speech overlap. Specifically, we observe relative word error rate reductions of 10% overall and 15% on low-overlap speech. This work represents an initial exploration of CTC-based enhancements for MTASR tasks, offering a new perspective on speaker disentanglement in multi-talker speech recognition.

Connectionist temporal classification (CTC) models are known to have peaky output distributions. Such behavior is not a problem for automatic speech recognition (ASR), but it can cause inaccurate forced alignments (FA), especially at finer granularity, e.g., phoneme level. This paper aims at alleviating the peaky behavior for CTC and improve its suitability for forced alignment generation, by leveraging label priors, so that the scores of alignment paths containing fewer blanks are boosted and maximized during training. As a result, our CTC model produces less peaky posteriors and is able to more accurately predict the offset of the tokens besides their onset. It outperforms the standard CTC model and a heuristics-based approach for obtaining CTC's token offset timestamps by 12-40% in phoneme and word boundary errors (PBE and WBE) measured on the Buckeye and TIMIT data. Compared with the most widely used FA toolkit Montreal Forced Aligner (MFA), our method performs similarly on PBE/WBE on Buckeye, yet falls behind MFA on TIMIT. Nevertheless, our method has a much simpler training pipeline and better runtime efficiency. Our training recipe and pretrained model are released in TorchAudio.

We introduce and detail an atypical neural network architecture, called time elastic neural network (teNN), for multivariate time series classification. The novelty compared to classical neural network architecture is that it explicitly incorporates time warping ability, as well as a new way of considering attention. In addition, this architecture is capable of learning a dropout strategy, thus optimizing its own architecture.Behind the design of this architecture, our overall objective is threefold: firstly, we are aiming at improving the accuracy of instance based classification approaches that shows quite good performances as far as enough training data is available. Secondly we seek to reduce the computational complexity inherent to these methods to improve their scalability. Ideally, we seek to find an acceptable balance between these first two criteria. And finally, we seek to enhance the explainability of the decision provided by this kind of neural architecture.The experiment demonstrates that the stochastic gradient descent implemented to train a teNN is quite effective. To the extent that the selection of some critical meta-parameters is correct, convergence is generally smooth and fast.While maintaining good accuracy, we get a drastic gain in scalability by first reducing the required number of reference time series, i.e. the number of teNN cells required. Secondly, we demonstrate that, during the training process, the teNN succeeds in reducing the number of neurons required within each cell. Finally, we show that the analysis of the activation and attention matrices as well as the reference time series after training provides relevant information to interpret and explain the classification results.The comparative study that we have carried out and which concerns around thirty diverse and multivariate datasets shows that the teNN obtains results comparable to those of the state of the art, in particular similar to those of a network mixing LSTM and CNN architectures for example.

This paper addresses the problem of detecting time series outliers, focusing on systems with repetitive behavior, such as industrial robots operating on production lines.Notable challenges arise from the fact that a task performed multiple times may exhibit different duration in each repetition and that the time series reported by the sensors are irregularly sampled because of data gaps. The anomaly detection approach presented in this paper consists of three stages.The first stage identifies the repetitive cycles in the lengthy time series and segments them into individual time series corresponding to one task cycle, while accounting for possible temporal distortions.The second stage computes a prototype for the cycles using a GPU-based barycenter algorithm, specifically tailored for very large time series.The third stage uses the prototype to detect abnormal cycles by computing an anomaly score for each cycle.The overall approach, named WarpEd Time Series ANomaly Detection (WETSAND), makes use of the Dynamic Time Warping algorithm and its variants because they are suited to the distorted nature of the time series.The experiments show that \wetsand scales to large signals, computes human-friendly prototypes, works with very little data, and outperforms some general purpose anomaly detection approaches such as autoencoders.

Entity alignment (EA) aims to identify entities across different knowledge graphs that represent the same real-world objects. Recent embedding-based EA methods have achieved state-of-the-art performance in EA yet faced interpretability challenges as they purely rely on the embedding distance and neglect the logic rules behind a pair of aligned entities. In this paper, we propose the Align-Subgraph Entity Alignment (ASGEA) framework to exploit logic rules from Align-Subgraphs. ASGEA uses anchor links as bridges to construct Align-Subgraphs and spreads along the paths across KGs, which distinguishes it from the embedding-based methods. Furthermore, we design an interpretable Path-based Graph Neural Network, ASGNN, to effectively identify and integrate the logic rules across KGs. We also introduce a node-level multi-modal attention mechanism coupled with multi-modal enriched anchors to augment the Align-Subgraph. Our experimental results demonstrate the superior performance of ASGEA over the existing embedding-based methods in both EA and Multi-Modal EA (MMEA) tasks.

Existing training criteria in automatic speech recognition(ASR) permit the model to freely explore more than one time alignments between the feature and label sequences. In this paper, we use entropy to measure a model's uncertainty, i.e. how it chooses to distribute the probability mass over the set of allowed alignments. Furthermore, we evaluate the effect of entropy regularization in encouraging the model to distribute the probability mass only on a smaller subset of allowed alignments. Experiments show that entropy regularization enables a much simpler decoding method without sacrificing word error rate, and provides better time alignment quality.

Despite the rapid progress on research in adversarial robustness of deep neural networks (DNNs), there is little principled work for the time-series domain. Since time-series data arises in diverse applications including mobile health, finance, and smart grid, it is important to verify and improve the robustness of DNNs for the time-series domain. In this paper, we propose a novel framework for the time-series domain referred as {\em Dynamic Time Warping for Adversarial Robustness (DTW-AR)} using the dynamic time warping measure. Theoretical and empirical evidence is provided to demonstrate the effectiveness of DTW over the standard Euclidean distance metric employed in prior methods for the image domain. We develop a principled algorithm justified by theoretical analysis to efficiently create diverse adversarial examples using random alignment paths. Experiments on diverse real-world benchmarks show the effectiveness of DTW-AR to fool DNNs for time-series data and to improve their robustness using adversarial training. The source code of DTW-AR algorithms is available at https://github.com/tahabelkhouja/DTW-AR