We present several methods to improve the generalisation of language identification (LID) systems to new speakers and to new domains. These methods involve Spectral augmentation, where spectrograms are masked in the frequency or time bands during training and CNN architectures that are pre-trained on the Imagenet dataset. The paper also introduces the novel Triplet Entropy Loss training method, which involves training a network simultaneously using Cross Entropy and Triplet loss. It was found that all three methods improved the generalisation of the models, though not significantly. Even though the models trained using Triplet Entropy Loss showed a better understanding of the languages and higher accuracies, it appears as though the models still memorise word patterns present in the spectrograms rather than learning the finer nuances of a language. The research shows that Triplet Entropy Loss has great potential and should be investigated further, not only in language identification tasks but any classification task.
Indian Institute of Technology Roorkee（印度理工学院鲁尔基分校）；Osaka Prefecture University（大阪府立大学）
In this paper, an end-to-end neural embedding system based on triplet loss and residual learning has been proposed for speech emotion recognition. The proposed system learns the embeddings from the emotional information of the speech utterances. The learned embeddings are used to recognize the emotions portrayed by given speech samples of various lengths. The proposed system implements Residual Neural Network architecture. It is trained using softmax pre-training and triplet loss function. The weights between the fully connected and embedding layers of the trained network are used to calculate…
Recent advances in cross-lingual text-to-speech (TTS) made it possible to synthesize speech in a language foreign to a monolingual speaker. However, there is still a large gap between the pronunciation of generated cross-lingual speech and that of native speakers in terms of naturalness and intelligibility. In this paper, a triplet training scheme is proposed to enhance the cross-lingual pronunciation by allowing previously unseen content and speaker combinations to be seen during training. Proposed method introduces an extra fine-tune stage with triplet loss during training, which efficiently…
Spoken term discovery from untranscribed speech audio could be achieved via a two-stage process. In the first stage, the unlabelled speech is decoded into a sequence of subword units that are learned and modelled in an unsupervised manner. In the second stage, partial sequence matching and clustering are performed on the decoded subword sequences, resulting in a set of discovered words or phrases. A limitation of this approach is that the results of subword decoding could be erroneous, and the errors would impact the subsequent steps. While Siamese/Triplet network is one approach to learn segm…
University of St. Gallen（圣加仑大学）；Reykjavik University（雷克雅未克大学）
Speech Emotion Recognition (SER) is crucial for human-computer interaction but still remains a challenging problem because of two major obstacles: data scarcity and imbalance. Many datasets for SER are substantially imbalanced, where data utterances of one class (most often Neutral) are much more frequent than those of other classes. Furthermore, only a few data resources are available for many existing spoken languages. To address these problems, we exploit a GAN-based augmentation model guided by a triplet network, to improve SER performance given imbalanced and insufficient training data. W…
University of Southern California（南加州大学）；University of Utah（犹他大学）
Speech encodes a wealth of information related to human behavior and has been used in a variety of automated behavior recognition tasks. However, extracting behavioral information from speech remains challenging including due to inadequate training data resources stemming from the often low occurrence frequencies of specific behavioral patterns. Moreover, supervised behavioral modeling typically relies on domain-specific construct definitions and corresponding manually-annotated data, rendering generalizing across domains challenging. In this paper, we exploit the stationary properties of huma…
Facultad de Estudios Superiores Cuautitlán（库奥蒂特兰高等研究学院）；Universidad Nacional Autónoma de México（墨西哥国立自治大学）；Universidad Abierta y a Distancia de México（墨西哥开放与远程大学）；University of Malta（马耳他大学）
With the advent of digital technology, it is more common that committed crimes or legal disputes involve some form of speech recording where the identity of a speaker is questioned [1]. In face of this situation, the field of forensic speaker identification has been looking to shed light on the problem by quantifying how much a speech recording belongs to a particular person in relation to a population. In this work, we explore the use of speech embeddings obtained by training a CNN using the triplet loss. In particular, we focus on the Spanish language which has not been extensively studies. …
In this study, we propose to investigate triplet loss for the purpose of an alternative feature representation for ASR. We consider a general non-semantic speech representation, which is trained with a self-supervised criteria based on triplet loss called TRILL, for acoustic modeling to represent the acoustic characteristics of each audio. This strategy is then applied to the CHiME-4 corpus and CRSS-UTDallas Fearless Steps Corpus, with emphasis on the 100-hour challenge corpus which consists of 5 selected NASA Apollo-11 channels. An analysis of the extracted embeddings provides the foundation …
University of Southern Queensland（南昆士兰大学）；Data61, CSIRO（联邦科学与工业研究组织数据61研究所）；Queensland University of Technology（昆士兰科技大学）；Imperial College London（帝国理工学院）；University of Augsburg（奥格斯堡大学）
Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems lack generalisation across different conditions. A key underlying reason for poor generalisation is the scarcity of emotion datasets, which is a significant roadblock to designing robust machine learning (ML) models. Recent works in SER focus on utilising multitask learning (MTL) methods to improve generalisation by learning shared representations. However, most of these studies propose MTL solutions with the requirement of meta labels for auxiliary tasks, which limits the training of SER systems. This pa…
University of Science and Technology of China（中国科学技术大学）；Alibaba DAMO Academy（阿里巴巴达摩院）；Rutgers University（罗格斯大学）
End-to-end speech-to-text translation (E2E-ST) is becoming increasingly popular due to the potential of its less error propagation, lower latency, and fewer parameters. Given the triplet training corpus $\langle speech, transcription, translation\rangle$, the conventional high-quality E2E-ST system leverages the $\langle speech, transcription\rangle$ pair to pre-train the model and then utilizes the $\langle speech, translation\rangle$ pair to optimize it further. However, this process only involves two-tuple data at each stage, and this loose coupling fails to fully exploit the association be…
TristouNet is a neural network architecture based on Long Short-Term Memory recurrent networks, meant to project speech sequences into a fixed-dimensional euclidean space. Thanks to the triplet loss paradigm used for training, the resulting sequence embeddings can be compared directly with the euclidean distance, for speaker comparison purposes. Experiments on short (between 500ms and 5s) speech turn comparison and speaker change detection show that TristouNet brings significant improvements over the current state-of-the-art techniques for both tasks.
CommonVoice-SpeechRE and RPG-MoGe: Advancing Speech Relation Extraction with a New Dataset and Multi-Order Generative Framework
School of Information Science and Technology, Dalian Maritime University（信息科学与技术学院，大连海事大学）；School of Computer Science and Technology, Dalian University of Technology（计算机科学与技术学院，大连理工大学）；College of Computer Science and Technology, Xinjiang Normal University（计算机科学与技术学院，新疆师范大学）；School of Computer and Electronic Information, Nanjing Normal University（计算机与电子信息学院，南京师范大学）；Adolescent Education and Intelligence Support Lab of Nanjing Normal University, Laboratory of Philosophy and Social Sciences at Universities in Jiangsu Province（南京师范大学青少年教育与智能支持实验室，江苏省高校哲学社会科学实验室）
Existing deep learning (DL) based speech enhancement approaches are generally optimised to minimise the distance between clean and enhanced speech features. These often result in improved speech quality however they suffer from a lack of generalisation and may not deliver the required speech intelligibility in real noisy situations. In an attempt to address these challenges, researchers have explored intelligibility-oriented (I-O) loss functions and integration of audio-visual (AV) information for more robust speech enhancement (SE). In this paper, we introduce DL based I-O SE algorithms explo…
Department of Computer Science, Columbia University（哥伦比亚大学计算机科学系）
The majority of existing speech emotion recognition models are trained and evaluated on a single corpus and a single language setting. These systems do not perform as well when applied in a cross-corpus and cross-language scenario. This paper presents results for speech emotion recognition for 4 languages in both single corpus and cross corpus setting. Additionally, since multi-task learning (MTL) with gender, naturalness and arousal as auxiliary tasks has shown to enhance the generalisation capabilities of the emotion models, this paper introduces language ID as another auxiliary task in MTL …
In this paper, we present the Blind Speech Separation and Dereverberation (BSSD) network, which performs simultaneous speaker separation, dereverberation and speaker identification in a single neural network. Speaker separation is guided by a set of predefined spatial cues. Dereverberation is performed by using neural beamforming, and speaker identification is aided by embedding vectors and triplet mining. We introduce a frequency-domain model which uses complex-valued neural networks, and a time-domain variant which performs beamforming in latent space. Further, we propose a block-online mode…
Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically motivated speech perception metrics as part of model training via a predictor network has recently gained interest. However, the performance of such predictors is limited by the distribution of metric scores that appear in the training data. In this work, we propose MetricGAN+/- (an extension of MetricGAN+, one such metric-motivated system) which introduces an additional network - a "de-generator" which attempts to imp…
Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings
Research Center for Information Technology Innovation, Academia Sinica（学术院信息科技创新研究中心）；College of Informatics, National Chengchi University（国立成功大学资讯学院）；Institute of Information Science, Academia Sinica（学术院信息科学研究所）；Institute of Communications Engineering, National Yang Ming Chiao Tung University（国立阳明交通大学通讯工程研究所）
Current deep learning (DL) based approaches to speech intelligibility enhancement in noisy environments are generally trained to minimise the distance between clean and enhanced speech features. These often result in improved speech quality however they suffer from a lack of generalisation and may not deliver the required speech intelligibility in everyday noisy situations. In an attempt to address these challenges, researchers have explored intelligibility-oriented (I-O) loss functions to train DL approaches for robust speech enhancement (SE). In this paper, we formulate a novel canonical cor…
University of Washington（华盛顿大学）；Google Research（谷歌研究院）
Systems that can associate images with their spoken audio captions are an important step towards visually grounded language learning. We describe a scalable method to automatically generate diverse audio for image captioning datasets. This supports pretraining deep networks for encoding both audio and images, which we do via a dual encoder that learns to align latent representations from both modalities. We show that a masked margin softmax loss for such models is superior to the standard triplet loss. We fine-tune these models on the Flickr8k Audio Captions Corpus and obtain state-of-the-art …
University of Cambridge（剑桥大学）；Amazon Alexa（亚马逊Alexa）
The diversity of speaker profiles in multi-speaker TTS systems is a crucial aspect of its performance, as it measures how many different speaker profiles TTS systems could possibly synthesize. However, this important aspect is often overlooked when building multi-speaker TTS systems and there is no established framework to evaluate this diversity. The reason behind is that most multi-speaker TTS systems are limited to generate speech signals with the same speaker profiles as its training data. They often use discrete speaker embedding vectors which have a one-to-one correspondence with individ…
Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation ability to unseen data, and its use in such open-set problems has been widespread. Therefore, this paper introduces a general approach to the large-margin softmax loss without any approximations to improve the quality of speaker embeddings for diarisation. Furthermore, a novel and simple way to stabilise training, when large-margin softmax is used, is propos…
University of Southern Queensland（南昆士兰大学）；Data61, CSIRO（联邦科学与工业研究组织Data61研究所）；Queensland University of Technology（昆士兰科技大学）；Imperial College London（帝国理工学院）；University of Augsburg（奥格斯堡大学）
Despite the recent advancement in speech emotion recognition (SER) within a single corpus setting, the performance of these SER systems degrades significantly for cross-corpus and cross-language scenarios. The key reason is the lack of generalisation in SER systems towards unseen conditions, which causes them to perform poorly in cross-corpus and cross-language settings. Recent studies focus on utilising adversarial methods to learn domain generalised representation for improving cross-corpus and cross-language SER to address this issue. However, many of these methods only focus on cross-corpu…
MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
Shanghai Jiao Tong University（上海交通大学）；Nanyang Technological University（南洋理工大学）；Queen Mary University of London（伦敦玛丽女王大学）；ByteDance（字节跳动）；Shanghai Innovation Institute（上海创新研究院）；Tsinghua University（清华大学）；University of Chinese Academy of Sciences（中国科学院大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）；The University of Texas at Austin（得克萨斯大学奥斯汀分校）
