Suwon Shon

Suwon Shon, Siddhant Arora, Chyi-Jiunn Lin et al. · cmu, deepmind

Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker recognition. In particular, there are not nearly as many SLU task benchmarks, and many of the existing ones use data that is not freely available to all researchers. Recent work has begun to introduce such benchmark datasets for several tasks. In this work, we introduce several new annotated SLU benchmark tasks based on freely available speech data, which complement existing benchmarks and address gaps in the SLU evaluation landscape. We contribute four tasks: question answering and summarization involve inference over longer speech sequences; named entity localization addresses the speech-specific task of locating the targeted content in the signal; dialog act classification identifies the function of a given speech utterance. We follow the blueprint of the Spoken Language Understanding Evaluation (SLUE) benchmark suite. In order to facilitate the development of SLU models that leverage the success of pre-trained speech representations, we will be publishing for each task (i) annotations for a relatively small fine-tuning set, (ii) annotated development and test sets, and (iii) baseline models for easy reproducibility and comparisons. In this work, we present the details of data collection and annotation and the performance of the baseline models. We also perform sensitivity analysis of pipeline models' performance (speech recognizer + text model) to the speech recognition accuracy, using more than 20 state-of-the-art speech recognition models.

Suwon Shon, Felix Wu, Kwangyoun Kim et al. · deepmind

Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of self-attention, they usually operate at the level of relatively short (e.g., utterance) segments. In this paper, we study the use of context, i.e., surrounding segments, during fine-tuning and propose a new approach called context-aware fine-tuning. We attach a context module on top of the last layer of a pre-trained model to encode the whole segment into a context embedding vector which is then used as an additional feature for the final prediction. During the fine-tuning stage, we introduce an auxiliary loss that encourages this context embedding vector to be similar to context vectors of surrounding segments. This allows the model to make predictions without access to these surrounding segments at inference time and requires only a tiny overhead compared to standard fine-tuned models. We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks: Automatic speech recognition (ASR), named entity recognition (NER), and sentiment analysis (SA). The results show that context-aware fine-tuning not only outperforms a standard fine-tuning baseline but also rivals a strong context injection baseline that uses neighboring speech segments during inference.

Zhaojiang Lin, Yong Xu, Kai Sun et al.

Wearable devices such as AI glasses are transforming voice assistants into always-available, hands-free collaborators that integrate seamlessly with daily life, but they also introduce challenges like egocentric audio affected by motion and noise, rapid micro-interactions, and the need to distinguish device-directed speech from background conversations. Existing benchmarks largely overlook these complexities, focusing instead on clean or generic conversational audio. To bridge this gap, we present WearVox, the first benchmark designed to rigorously evaluate voice assistants in realistic wearable scenarios. WearVox comprises 3,842 multi-channel, egocentric audio recordings collected via AI glasses across five diverse tasks including Search-Grounded QA, Closed-Book QA, Side-Talk Rejection, Tool Calling, and Speech Translation, spanning a wide range of indoor and outdoor environments and acoustic conditions. Each recording is accompanied by rich metadata, enabling nuanced analysis of model performance under real-world constraints. We benchmark leading proprietary and open-source speech Large Language Models (SLLMs) and find that most real-time SLLMs achieve accuracies on WearVox ranging from 29% to 59%, with substantial performance degradation on noisy outdoor audio, underscoring the difficulty and realism of the benchmark. Additionally, we conduct a case study with two new SLLMs that perform inference with single-channel and multi-channel audio, demonstrating that multi-channel audio inputs significantly enhance model robustness to environmental noise and improve discrimination between device-directed and background speech. Our results highlight the critical importance of spatial audio cues for context-aware voice assistants and establish WearVox as a comprehensive testbed for advancing wearable voice AI research.

Roshan Sharma, Suwon Shon, Mark Lindsey et al.

Reference summaries for abstractive speech summarization require human annotation, which can be performed by listening to an audio recording or by reading textual transcripts of the recording. In this paper, we examine whether summaries based on annotators listening to the recordings differ from those based on annotators reading transcripts. Using existing intrinsic evaluation based on human evaluation, automatic metrics, LLM-based evaluation, and a retrieval-based reference-free method. We find that summaries are indeed different based on the source modality, and that speech-based summaries are more factually consistent and information-selective than transcript-based summaries. Meanwhile, transcript-based summaries are impacted by recognition errors in the source, and expert-written summaries are more informative and reliable. We make all the collected data and analysis code public(https://github.com/cmu-mlsp/interview_humanssum) to facilitate the reproduction of our work and advance research in this area.

Chien-yu Huang, Wei-Chih Chen, Shu-wen Yang et al. · cmu, mit

Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spoken language model that comprehends a wide range of natural language instructions is critical for bridging communication gaps and facilitating more intuitive interactions. However, the absence of a comprehensive evaluation benchmark poses a significant challenge. We present Dynamic-SUPERB Phase-2, an open and evolving benchmark for the comprehensive evaluation of instruction-based universal speech models. Building upon the first generation, this second version incorporates 125 new tasks contributed collaboratively by the global research community, expanding the benchmark to a total of 180 tasks, making it the largest benchmark for speech and audio evaluation. While the first generation of Dynamic-SUPERB was limited to classification tasks, Dynamic-SUPERB Phase-2 broadens its evaluation capabilities by introducing a wide array of novel and diverse tasks, including regression and sequence generation, across speech, music, and environmental audio. Evaluation results show that no model performed well universally. SALMONN-13B excelled in English ASR and Qwen2-Audio-7B-Instruct showed high accuracy in emotion recognition, but current models still require further innovations to handle a broader range of tasks. We open-source all task data and the evaluation pipeline at https://github.com/dynamic-superb/dynamic-superb.

Siddhant Arora, Ankita Pasad, Chung-Ming Chien et al.

The Spoken Language Understanding Evaluation (SLUE) suite of benchmark tasks was recently introduced to address the need for open resources and benchmarking of complex spoken language understanding (SLU) tasks, including both classification and sequence generation tasks, on natural speech. The benchmark has demonstrated preliminary success in using pre-trained speech foundation models (SFM) for these SLU tasks. However, the community still lacks a fine-grained understanding of the comparative utility of different SFMs. Inspired by this, we ask: which SFMs offer the most benefits for these complex SLU tasks, and what is the most effective approach for incorporating these SFMs? To answer this, we perform an extensive evaluation of multiple supervised and self-supervised SFMs using several evaluation protocols: (i) frozen SFMs with a lightweight prediction head, (ii) frozen SFMs with a complex prediction head, and (iii) fine-tuned SFMs with a lightweight prediction head. Although the supervised SFMs are pre-trained on much more speech recognition data (with labels), they do not always outperform self-supervised SFMs; the latter tend to perform at least as well as, and sometimes better than, supervised SFMs, especially on the sequence generation tasks in SLUE. While there is no universally optimal way of incorporating SFMs, the complex prediction head gives the best performance for most tasks, although it increases the inference time. We also introduce an open-source toolkit and performance leaderboard, SLUE-PERB, for these tasks and modeling strategies.

Suwon Shon, Ankita Pasad, Felix Wu et al.

Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in higher-level spoken language understanding tasks, including using end-to-end models, but there are fewer annotated datasets for such tasks. At the same time, recent work shows the possibility of pre-training generic representations and then fine-tuning for several tasks using relatively little labeled data. We propose to create a suite of benchmark tasks for Spoken Language Understanding Evaluation (SLUE) consisting of limited-size labeled training sets and corresponding evaluation sets. This resource would allow the research community to track progress, evaluate pre-trained representations for higher-level tasks, and study open questions such as the utility of pipeline versus end-to-end approaches. We present the first phase of the SLUE benchmark suite, consisting of named entity recognition, sentiment analysis, and ASR on the corresponding datasets. We focus on naturally produced (not read or synthesized) speech, and freely available datasets. We provide new transcriptions and annotations on subsets of the VoxCeleb and VoxPopuli datasets, evaluation metrics and results for baseline models, and an open-source toolkit to reproduce the baselines and evaluate new models.

Suwon Shon, Kwangyoun Kim, Prashant Sridhar et al.

When performing tasks like automatic speech recognition or spoken language understanding for a given utterance, access to preceding text or audio provides contextual information can improve performance. Considering the recent advances in generative large language models (LLM), we hypothesize that an LLM could generate useful context information using the preceding text. With appropriate prompts, LLM could generate a prediction of the next sentence or abstractive text like titles or topics. In this paper, we study the use of LLM-generated context information and propose an approach to distill the generated information during fine-tuning of self-supervised speech models, which we refer to as generative context-aware fine-tuning. This approach allows the fine-tuned model to make improved predictions without access to the true surrounding segments or to the LLM at inference time, while requiring only a very small additional context module. We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks: automatic speech recognition, named entity recognition, and sentiment analysis. The results show that generative context-aware fine-tuning outperforms a context injection fine-tuning approach that accesses the ground-truth previous text, and is competitive with a generative context injection fine-tuning approach that requires the LLM at inference time.

Suwon Shon, Kwangyoun Kim, Yi-Te Hsu et al.

The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an LLM, trained on diverse tasks. We propose the use of discrete speech units (DSU), rather than continuous-valued speech encoder outputs, that are converted to the LLM token embedding space using the speech adapter. We generate DSU using a self-supervised speech encoder followed by k-means clustering. The proposed model shows robust performance on speech inputs from seen/unseen domains and instruction-following capability in spoken question answering. We also explore various types of DSU extracted from different layers of the self-supervised speech encoder, as well as Mel frequency Cepstral Coefficients (MFCC). Our findings suggest that the ASR task and datasets are not crucial in instruction-tuning for spoken question answering tasks.

Jiyang Tang, Kwangyoun Kim, Suwon Shon et al.

In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the effectiveness and robustness of automatic speech recognition (ASR) contextual biasing without introducing additional parameters. A common challenge in previous literature is that the word error rate (WER) reduction brought by contextual biasing diminishes as the number of bias phrases increases. To address this challenge, we employ a GA loss as an additional training objective besides the Transducer loss. The proposed GA loss aims to teach the cross attention how to align bias phrases with text tokens or audio frames. Compared to studies with similar motivations, the proposed loss operates directly on the cross attention weights and is easier to implement. Through extensive experiments based on Conformer Transducer with Contextual Adapter, we demonstrate that the proposed method not only leads to a lower WER but also retains its effectiveness as the number of bias phrases increases. Specifically, the GA loss decreases the WER of rare vocabularies by up to 19.2% on LibriSpeech compared to the contextual biasing baseline, and up to 49.3% compared to a vanilla Transducer.

Yifan Peng, Kwangyoun Kim, Felix Wu et al.

Conformer, a convolution-augmented Transformer variant, has become the de facto encoder architecture for speech processing due to its superior performance in various tasks, including automatic speech recognition (ASR), speech translation (ST) and spoken language understanding (SLU). Recently, a new encoder called E-Branchformer has outperformed Conformer in the LibriSpeech ASR benchmark, making it promising for more general speech applications. This work compares E-Branchformer and Conformer through extensive experiments using different types of end-to-end sequence-to-sequence models. Results demonstrate that E-Branchformer achieves comparable or better performance than Conformer in almost all evaluation sets across 15 ASR, 2 ST, and 3 SLU benchmarks, while being more stable during training. We will release our training configurations and pre-trained models for reproducibility, which can benefit the speech community.

Ankita Pasad, Felix Wu, Suwon Shon et al.

Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect for each new task and domain. However, recent advances in self-supervised speech representations have made it feasible to consider learning SLU models with limited labeled data. In this work we focus on low-resource spoken named entity recognition (NER) and address the question: Beyond self-supervised pre-training, how can we use external speech and/or text data that are not annotated for the task? We draw on a variety of approaches, including self-training, knowledge distillation, and transfer learning, and consider their applicability to both end-to-end models and pipeline (speech recognition followed by text NER model) approaches. We find that several of these approaches improve performance in resource-constrained settings beyond the benefits from pre-trained representations alone. Compared to prior work, we find improved F1 scores of up to 16%. While the best baseline model is a pipeline approach, the best performance when using external data is ultimately achieved by an end-to-end model. We provide detailed comparisons and analyses, showing for example that end-to-end models are able to focus on the more NER-specific words.

Suwon Shon, Pablo Brusco, Jing Pan et al.

In this paper, we explore the use of pre-trained language models to learn sentiment information of written texts for speech sentiment analysis. First, we investigate how useful a pre-trained language model would be in a 2-step pipeline approach employing Automatic Speech Recognition (ASR) and transcripts-based sentiment analysis separately. Second, we propose a pseudo label-based semi-supervised training strategy using a language model on an end-to-end speech sentiment approach to take advantage of a large, but unlabeled speech dataset for training. Although spoken and written texts have different linguistic characteristics, they can complement each other in understanding sentiment. Therefore, the proposed system can not only model acoustic characteristics to bear sentiment-specific information in speech signals, but learn latent information to carry sentiments in the text representation. In these experiments, we demonstrate the proposed approaches improve F1 scores consistently compared to systems without a language model. Moreover, we also show that the proposed framework can reduce 65% of human supervision by leveraging a large amount of data without human sentiment annotation and boost performance in a low-resource condition where the human sentiment annotation is not available enough.

Achintya kr. Sarkar, Zheng-Hua Tan, Hao Tang et al.

There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker verification (TD-SV). However, a moderate success has been achieved. A recent study [1] presented a time contrastive learning (TCL) concept to explore the non-stationarity of brain signals for classification of brain states. Speech signals have similar non-stationarity property, and TCL further has the advantage of having no need for labeled data. We therefore present a TCL based BN feature extraction method. The method uniformly partitions each speech utterance in a training dataset into a predefined number of multi-frame segments. Each segment in an utterance corresponds to one class, and class labels are shared across utterances. DNNs are then trained to discriminate all speech frames among the classes to exploit the temporal structure of speech. In addition, we propose a segment-based unsupervised clustering algorithm to re-assign class labels to the segments. TD-SV experiments were conducted on the RedDots challenge database. The TCL-DNNs were trained using speech data of fixed pass-phrases that were excluded from the TD-SV evaluation set, so the learned features can be considered phrase-independent. We compare the performance of the proposed TCL bottleneck (BN) feature with those of short-time cepstral features and BN features extracted from DNNs discriminating speakers, pass-phrases, speaker+pass-phrase, as well as monophones whose labels and boundaries are generated by three different automatic speech recognition (ASR) systems. Experimental results show that the proposed TCL-BN outperforms cepstral features and speaker+pass-phrase discriminant BN features, and its performance is on par with those of ASR derived BN features. Moreover,....

Suwon Shon, Najim Dehak, Douglas Reynolds et al.

The Multi-target Challenge aims to assess how well current speech technology is able to determine whether or not a recorded utterance was spoken by one of a large number of blacklisted speakers. It is a form of multi-target speaker detection based on real-world telephone conversations. Data recordings are generated from call center customer-agent conversations. The task is to measure how accurately one can detect 1) whether a test recording is spoken by a blacklisted speaker, and 2) which specific blacklisted speaker was talking. This paper outlines the challenge and provides its baselines, results, and discussions.

Suwon Shon, Hao Tang, James Glass

In this paper, we propose VoiceID loss, a novel loss function for training a speech enhancement model to improve the robustness of speaker verification. In contrast to the commonly used loss functions for speech enhancement such as the L2 loss, the VoiceID loss is based on the feedback from a speaker verification model to generate a ratio mask. The generated ratio mask is multiplied pointwise with the original spectrogram to filter out unnecessary components for speaker verification. In the experiments, we observed that the enhancement network, after training with the VoiceID loss, is able to ignore a substantial amount of time-frequency bins, such as those dominated by noise, for verification. The resulting model consistently improves the speaker verification system on both clean and noisy conditions.

Seongkyu Mun, Suwon Shon

In a recent acoustic scene classification (ASC) research field, training and test device channel mismatch have become an issue for the real world implementation. To address the issue, this paper proposes a channel domain conversion using factorized hierarchical variational autoencoder. Proposed method adapts both the source and target domain to a pre-defined specific domain. Unlike the conventional approach, the relationship between the target and source domain and information of each domain are not required in the adaptation process. Based on the experimental results using the IEEE detection and classification of acoustic scenes and event 2018 task 1-B dataset and the baseline system, it is shown that the proposed approach can mitigate the channel mismatching issue of different recording devices.

Suwon Shon, Ahmed Ali, James Glass

End-to-end deep learning language or dialect identification systems operate on the spectrogram or other acoustic feature and directly generate identification scores for each class. An important issue for end-to-end systems is to have some knowledge of the application domain, because the system can be vulnerable to use cases that were not seen in the training phase; such a scenario is often referred to as a domain mismatched condition. In general, we assume that there is enough variation in the training dataset to expose the system to multiple domains. In this work, we study how to best make use a training dataset in order to have maximum effectiveness on unknown target domains. Our goal is to process the input without any knowledge of the target domain while preserving robust performance on other domains as well. To accomplish this objective, we propose a domain attentive fusion approach for end-to-end dialect/language identification systems. To help with experimentation, we collect a dataset from three different domains, and create experimental protocols for a domain mismatched condition. The results of our proposed approach, which were tested on a variety of broadcast and YouTube data, shows significant performance gain compared to traditional approaches, even without any prior target domain information.

Suwon Shon, Tae-Hyun Oh, James Glass

In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the association of voice and face, we propose an attention-based end-to-end neural network that learns multi-sensory associations for the task of person verification. The attention mechanism in our proposed network learns to conditionally select a salient modality between speech and facial representations that provides a balance between complementary inputs. By virtue of this capability, the network is robust to missing or corrupted data from either modality. In the VoxCeleb2 dataset, we show that our method performs favorably against competing multi-modal methods. Even for extreme cases of large corruption or an entirely missing modality, our method demonstrates robustness over other unimodal methods.

Suwon Shon, Younggun Lee, Taesu Kim

This paper describes a fast speaker search system to retrieve segments of the same voice identity in the large-scale data. A recent study shows that Locality Sensitive Hashing (LSH) enables quick retrieval of a relevant voice in the large-scale data in conjunction with i-vector while maintaining accuracy. In this paper, we proposed Random Speaker-variability Subspace (RSS) projection to map a data into LSH based hash tables. We hypothesized that rather than projecting on completely random subspace without considering data, projecting on randomly generated speaker variability space would give more chance to put the same speaker representation into the same hash bins, so we can use less number of hash tables. Multiple RSS can be generated by randomly selecting a subset of speakers from a large speaker cohort. From the experimental result, the proposed approach shows 100 times and 7 times faster than the linear search and LSH, respectively

Younggun Lee, Suwon Shon, Taesu Kim

Although there are more than 6,500 languages in the world, the pronunciations of many phonemes sound similar across the languages. When people learn a foreign language, their pronunciation often reflects their native language's characteristics. This motivates us to investigate how the speech synthesis network learns the pronunciation from datasets from different languages. In this study, we are interested in analyzing and taking advantage of multilingual speech synthesis network. First, we train the speech synthesis network bilingually in English and Korean and analyze how the network learns the relations of phoneme pronunciation between the languages. Our experimental result shows that the learned phoneme embedding vectors are located closer if their pronunciations are similar across the languages. Consequently, the trained networks can synthesize the English speakers' Korean speech and vice versa. Using this result, we propose a training framework to utilize information from a different language. To be specific, we pre-train a speech synthesis network using datasets from both high-resource language and low-resource language, then we fine-tune the network using the low-resource language dataset. Finally, we conducted more simulations on 10 different languages to show it is generally extendable to other languages.

Suwon Shon, Wei-Ning Hsu, James Glass

In this paper, we explore the use of a factorized hierarchical variational autoencoder (FHVAE) model to learn an unsupervised latent representation for dialect identification (DID). An FHVAE can learn a latent space that separates the more static attributes within an utterance from the more dynamic attributes by encoding them into two different sets of latent variables. Useful factors for dialect identification, such as phonetic or linguistic content, are encoded by a segmental latent variable, while irrelevant factors that are relatively constant within a sequence, such as a channel or a speaker information, are encoded by a sequential latent variable. The disentanglement property makes the segmental latent variable less susceptible to channel and speaker variation, and thus reduces degradation from channel domain mismatch. We demonstrate that on fully-supervised DID tasks, an end-to-end model trained on the features extracted from the FHVAE model achieves the best performance, compared to the same model trained on conventional acoustic features and an i-vector based system. Moreover, we also show that the proposed approach can leverage a large amount of unlabeled data for FHVAE training to learn domain-invariant features for DID, and significantly improve the performance in a low-resource condition, where the labels for the in-domain data are not available.

Suwon Shon, Hao Tang, James Glass

In this paper, we propose a Convolutional Neural Network (CNN) based speaker recognition model for extracting robust speaker embeddings. The embedding can be extracted efficiently with linear activation in the embedding layer. To understand how the speaker recognition model operates with text-independent input, we modify the structure to extract frame-level speaker embeddings from each hidden layer. We feed utterances from the TIMIT dataset to the trained network and use several proxy tasks to study the networks ability to represent speech input and differentiate voice identity. We found that the networks are better at discriminating broad phonetic classes than individual phonemes. In particular, frame-level embeddings that belong to the same phonetic classes are similar (based on cosine distance) for the same speaker. The frame level representation also allows us to analyze the networks at the frame level, and has the potential for other analyses to improve speaker recognition.

Suwon Shon, Najim Dehak, Douglas Reynolds et al.

The Multitarget Challenge aims to assess how well current speech technology is able to determine whether or not a recorded utterance was spoken by one of a large number of 'blacklisted' speakers. It is a form of multi-target speaker detection based on real-world telephone conversations. Data recordings are generated from call center customer-agent conversations. Each conversation is represented by a single i-vector. Given a pool of training and development data from non-Blacklist and Blacklist speakers, the task is to measure how accurately one can detect 1) whether a test recording is spoken by a Blacklist speaker, and 2) which specific Blacklist speaker was talking.

Suwon Shon, Ahmed Ali, James Glass

Dialect identification (DID) is a special case of general language identification (LID), but a more challenging problem due to the linguistic similarity between dialects. In this paper, we propose an end-to-end DID system and a Siamese neural network to extract language embeddings. We use both acoustic and linguistic features for the DID task on the Arabic dialectal speech dataset: Multi-Genre Broadcast 3 (MGB-3). The end-to-end DID system was trained using three kinds of acoustic features: Mel-Frequency Cepstral Coefficients (MFCCs), log Mel-scale Filter Bank energies (FBANK) and spectrogram energies. We also investigated a dataset augmentation approach to achieve robust performance with limited data resources. Our linguistic feature research focused on learning similarities and dissimilarities between dialects using the Siamese network, so that we can reduce feature dimensionality as well as improve DID performance. The best system using a single feature set achieves 73% accuracy, while a fusion system using multiple features yields 78% on the MGB-3 dialect test set consisting of 5 dialects. The experimental results indicate that FBANK features achieve slightly better results than MFCCs. Dataset augmentation via speed perturbation appears to add significant robustness to the system. Although the Siamese network with language embeddings did not achieve as good a result as the end-to-end DID system, the two approaches had good synergy when combined together in a fused system.

Suwon Shon, Ahmed Ali, James Glass

In order to successfully annotate the Arabic speech con- tent found in open-domain media broadcasts, it is essential to be able to process a diverse set of Arabic dialects. For the 2017 Multi-Genre Broadcast challenge (MGB-3) there were two possible tasks: Arabic speech recognition, and Arabic Dialect Identification (ADI). In this paper, we describe our efforts to create an ADI system for the MGB-3 challenge, with the goal of distinguishing amongst four major Arabic dialects, as well as Modern Standard Arabic. Our research fo- cused on dialect variability and domain mismatches between the training and test domain. In order to achieve a robust ADI system, we explored both Siamese neural network models to learn similarity and dissimilarities among Arabic dialects, as well as i-vector post-processing to adapt domain mismatches. Both Acoustic and linguistic features were used for the final MGB-3 submissions, with the best primary system achieving 75% accuracy on the official 10hr test set.

Seongkyu Mun, Minkyu Shin, Suwon Shon et al.

Recent acoustic event classification research has focused on training suitable filters to represent acoustic events. However, due to limited availability of target event databases and linearity of conventional filters, there is still room for improving performance. By exploiting the non-linear modeling of deep neural networks (DNNs) and their ability to learn beyond pre-trained environments, this letter proposes a DNN-based feature extraction scheme for the classification of acoustic events. The effectiveness and robustness to noise of the proposed method are demonstrated using a database of indoor surveillance environments.

Suwon Shon, Seongkyu Mun, Hanseok Ko

Recently in speaker recognition, performance degradation due to the channel domain mismatched condition has been actively addressed. However, the mismatches arising from language is yet to be sufficiently addressed. This paper proposes an approach which employs recursive whitening transformation to mitigate the language mismatched condition. The proposed method is based on the multiple whitening transformation, which is intended to remove un-whitened residual components in the dataset associated with i-vector length normalization. The experiments were conducted on the Speaker Recognition Evaluation 2016 trials of which the task is non-English speaker recognition using development dataset consist of both a large scale out-of-domain (English) dataset and an extremely low-quantity in-domain (non-English) dataset. For performance comparison, we develop a state-of- the-art system using deep neural network and bottleneck feature, which is based on a phonetically aware model. From the experimental results, along with other prior studies, effectiveness of the proposed method on language mismatched condition is validated.

Suwon Shon, Seongkyu Mun, Wooil Kim et al.

In real-life conditions, mismatch between development and test domain degrades speaker recognition performance. To solve the issue, many researchers explored domain adaptation approaches using matched in-domain dataset. However, adaptation would be not effective if the dataset is insufficient to estimate channel variability of the domain. In this paper, we explore the problem of performance degradation under such a situation of insufficient channel information. In order to exploit limited in-domain dataset effectively, we propose an unsupervised domain adaptation approach using Autoencoder based Domain Adaptation (AEDA). The proposed approach combines an autoencoder with a denoising autoencoder to adapt resource-rich development dataset to test domain. The proposed technique is evaluated on the Domain Adaptation Challenge 13 experimental protocols that is widely used in speaker recognition for domain mismatched condition. The results show significant improvements over baselines and results from other prior studies.

Suwon Shon, Hanseok Ko

Korea University Intelligent Signal Processing Lab. (KU-ISPL) developed speaker recognition system for SRE16 fixed training condition. Data for evaluation trials are collected from outside North America, spoken in Tagalog and Cantonese while training data only is spoken English. Thus, main issue for SRE16 is compensating the discrepancy between different languages. As development dataset which is spoken in Cebuano and Mandarin, we could prepare the evaluation trials through preliminary experiments to compensate the language mismatched condition. Our team developed 4 different approaches to extract i-vectors and applied state-of-the-art techniques as backend. To compensate language mismatch, we investigated and endeavored unique method such as unsupervised language clustering, inter language variability compensation and gender/language dependent score normalization.

Suwon Shon, Seongkyu Mun, David Han et al.

A novel non-negative matrix factorization (NMF) based subband decomposition in frequency spatial domain for acoustic source localization using a microphone array is introduced. The proposed method decomposes source and noise subband and emphasises source dominant frequency bins for more accurate source representation. By employing NMF, delay basis vectors and their subband information in frequency spatial domain for each frame is extracted. The proposed algorithm is evaluated in both simulated noise and real noise with a speech corpus database. Experimental results clearly indicate that the algorithm performs more accurately than other conventional algorithms under both reverberant and noisy acoustic environments.

Suwon Shon, Seongkyu Mun, John H. L. Hansen et al.

In language recognition, the task of rejecting/differentiating closely spaced versus acoustically far spaced languages remains a major challenge. For confusable closely spaced languages, the system needs longer input test duration material to obtain sufficient information to distinguish between languages. Alternatively, if languages are distinct and not acoustically/linguistically similar to others, duration is not a sufficient remedy. The solution proposed here is to explore duration distribution analysis for near/far languages based on the Language Recognition i-Vector Machine Learning Challenge 2015 (LRiMLC15) database. Using this knowledge, we propose a likelihood ratio based fusion approach that leveraged both score and duration information. The experimental results show that the use of duration and score fusion improves language recognition performance by 5% relative in LRiMLC15 cost.