We propose direct multimodal few-shot models that learn a shared embedding space of spoken words and images from only a few paired examples. Imagine an agent is shown an image along with a spoken word describing the object in the picture, e.g. pen, book and eraser. After observing a few paired examples of each class, the model is asked to identify the "book" in a set of unseen pictures. Previous work used a two-step indirect approach relying on learned unimodal representations: speech-speech and image-image comparisons are performed across the support set of given speech-image pairs. We propose two direct models which instead learn a single multimodal space where inputs from different modalities are directly comparable: a multimodal triplet network (MTriplet) and a multimodal correspondence autoencoder (MCAE). To train these direct models, we mine speech-image pairs: the support set is used to pair up unlabelled in-domain speech and images. In a speech-to-image digit matching task, direct models outperform indirect models, with the MTriplet achieving the best multimodal five-shot accuracy. We show that the improvements are due to the combination of unsupervised and transfer learning in the direct models, and the absence of two-step compounding errors.
DiDi Chuxing（滴滴出行）；DiDi Research America（滴滴美国研究院）；Peking University（北京大学）
Speech emotion recognition is a challenging problem because human convey emotions in subtle and complex ways. For emotion recognition on human speech, one can either extract emotion related features from audio signals or employ speech recognition techniques to generate text from speech and then apply natural language processing to analyze the sentiment. Further, emotion recognition will be beneficial from using audio-textual multimodal information, it is not trivial to build a system to learn from multimodality. One can build models for two input sources separately and combine them in a decisi…
We address a challenging and practical task of labeling questions in speech in real time during telephone calls to emergency medical services in English, which embeds within a broader decision support system for emergency call-takers. We propose a novel multimodal approach to real-time sequence labeling in speech. Our model treats speech and its own textual representation as two separate modalities or views, as it jointly learns from streamed audio and its noisy transcription into text via automatic speech recognition. Our results show significant gains of jointly learning from the two modalit…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Le Mans University（勒芒大学）
We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation learning framework. Unlike previous works on speech representation learning, which learns multilingual contextual speech embedding at the resolution of an acoustic frame (10-20ms), this work focuses on learning multimodal (speech-text) multilingual speech embedding at the resolution of a sentence (5-10s) such that the embedding vector space is semantically aligned across different languages. We combine state-of-the-art multilingual acoustic frame-level speech representation learning mo…
Multimodal learning allows us to leverage information from multiple sources (visual, acoustic and text), similar to our experience of the real world. However, it is currently unclear to what extent auxiliary modalities improve performance over unimodal models, and under what circumstances the auxiliary modalities are useful. We examine the utility of the auxiliary visual context in Multimodal Automatic Speech Recognition in adversarial settings, where we deprive the models from partial audio signal during inference time. Our experiments show that while MMASR models show significant gains over …
End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which are difficult and expensive to obtain. Fortunately, the supervised data for automatic speech recognition (ASR) and machine translation (MT) are usually more accessible, making zero-shot speech translation a potential direction. Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space, resulting in much worse p…
Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model
NTIS – New Technologies for the Information Society（NTIS——信息社会新技术研究院）；Faculty of Applied Sciences（应用科学学院）；University of West Bohemia in Pilsen（西波希米亚大学（比尔森））
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）
Previously, a machine speech chain, which is based on sequence-to-sequence deep learning, was proposed to mimic speech perception and production behavior. Such chains separately processed listening and speaking by automatic speech recognition (ASR) and text-to-speech synthesis (TTS) and simultaneously enabled them to teach each other in semi-supervised learning when they received unpaired data. Unfortunately, this speech chain study is limited to speech and textual modalities. In fact, natural communication is actually multimodal and involves both auditory and visual sensory systems. Although …
Nara Institute of Science and Technology（奈良科学技术研究所）；RIKEN（理化学研究所）
Previous research has proposed a machine speech chain to enable automatic speech recognition (ASR) and text-to-speech synthesis (TTS) to assist each other in semi-supervised learning and to avoid the need for a large amount of paired speech and text data. However, that framework still requires a large amount of unpaired (speech or text) data. A prototype multimodal machine chain was then explored to further reduce the need for a large amount of unpaired data, which could improve ASR or TTS even when no more speech or text data were available. Unfortunately, this framework relied on the image r…
Automatic emotion recognition is one of the central concerns of the Human-Computer Interaction field as it can bridge the gap between humans and machines. Current works train deep learning models on low-level data representations to solve the emotion recognition task. Since emotion datasets often have a limited amount of data, these approaches may suffer from overfitting, and they may learn based on superficial cues. To address these issues, we propose a novel cross-representation speech model, inspired by disentanglement representation learning, to perform emotion recognition on wav2vec 2.0 s…
Meta AI Research（Meta人工智能研究院）；Google Research（谷歌研究院）；Carnegie Mellon University（卡内基梅隆大学）
We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of the machine translation FLoRes-101 benchmark, with approximately 12 hours of speech supervision per language. FLEURS can be used for a variety of speech tasks, including Automatic Speech Recognition (ASR), Speech Language Identification (Speech LangID), Translation and Retrieval. In this paper, we provide baselines for the tasks based on multilingual pre-trained models like mSLAM. The goal of FLEURS is to enable spee…
Southern University of Science and Technology（南方科技大学）；Microsoft China（微软中国）
Machine Speech Chain, which integrates both end-to-end (E2E) automatic speech recognition (ASR) and text-to-speech (TTS) into one circle for joint training, has been proven to be effective in data augmentation by leveraging large amounts of unpaired data. In this paper, we explore the TTS->ASR pipeline in speech chain to do domain adaptation for both neural TTS and E2E ASR models, with only text data from target domain. We conduct experiments by adapting from audiobook domain (LibriSpeech) to presentation domain (TED-LIUM), there is a relative word error rate (WER) reduction of 10% for the E2E…
Carnegie Mellon University（卡内基梅隆大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Edinburgh（爱丁堡大学）；Indian Institute of Technology Bombay（印度理工学院孟买分校）
In this work, we seek to build effective code-switched (CS) automatic speech recognition systems (ASR) under the zero-shot setting where no transcribed CS speech data is available for training. Previously proposed frameworks which conditionally factorize the bilingual task into its constituent monolingual parts are a promising starting point for leveraging monolingual data efficiently. However, these methods require the monolingual modules to perform language segmentation. That is, each monolingual module has to simultaneously detect CS points and transcribe speech segments of one language whi…
Recently, end-to-end speech translation (ST) has gained significant attention as it avoids error propagation. However, the approach suffers from data scarcity. It heavily depends on direct ST data and is less efficient in making use of speech transcription and text translation data, which is often more easily available. In the related field of multilingual text translation, several techniques have been proposed for zero-shot translation. A main idea is to increase the similarity of semantically similar sentences in different languages. We investigate whether these ideas can be applied to speec…
National Institute of Informatics（国立信息学研究所）；Unversity of Edinburgh（爱丁堡大学）
This paper proposes a new architecture for speaker adaptation of multi-speaker neural-network speech synthesis systems, in which an unseen speaker's voice can be built using a relatively small amount of speech data without transcriptions. This is sometimes called "unsupervised speaker adaptation". More specifically, we concatenate the layers to the audio inputs when performing unsupervised speaker adaptation while we concatenate them to the text inputs when synthesizing speech from text. Two new training schemes for the new architecture are also proposed in this paper. These training schemes a…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）
In previous work, we developed a closed-loop speech chain model based on deep learning, in which the architecture enabled the automatic speech recognition (ASR) and text-to-speech synthesis (TTS) components to mutually improve their performance. This was accomplished by the two parts teaching each other using both labeled and unlabeled data. This approach could significantly improve model performance within a single-speaker speech dataset, but only a slight increase could be gained in multi-speaker tasks. Furthermore, the model is still unable to handle unseen speakers. In this paper, we prese…
We consider the task of multimodal one-shot speech-image matching. An agent is shown a picture along with a spoken word describing the object in the picture, e.g. cookie, broccoli and ice-cream. After observing one paired speech-image example per class, it is shown a new set of unseen pictures, and asked to pick the "ice-cream". Previous work attempted to tackle this problem using transfer learning: supervised models are trained on labelled background data not containing any of the one-shot classes. Here we compare transfer learning to unsupervised models trained on unlabelled in-domain data. …
In this work, we explore a multimodal semi-supervised learning approach for punctuation prediction by learning representations from large amounts of unlabelled audio and text data. Conventional approaches in speech processing typically use forced alignment to encoder per frame acoustic features to word level features and perform multimodal fusion of the resulting acoustic and lexical representations. As an alternative, we explore attention based multimodal fusion and compare its performance with forced alignment based fusion. Experiments conducted on the Fisher corpus show that our proposed ap…
We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art sequence-to-sequence based system with a Variational AutoEncoder (VAE) and a Householder Flow. The proposed system provides a 22% KL-divergence reduction while jointly improving perceptual metrics over state-of-the-art. At synthesis time we use one example of expressive style as a reference input to the encoder for generating any text in the desired style. Perceptual MUSHRA evaluati…
Standard approaches to hate speech detection rely on sufficient available hate speech annotations. Extending previous work that repurposes natural language inference (NLI) models for zero-shot text classification, we propose a simple approach that combines multiple hypotheses to improve English NLI-based zero-shot hate speech detection. We first conduct an error analysis for vanilla NLI-based zero-shot hate speech detection and then develop four strategies based on this analysis. The strategies use multiple hypotheses to predict various aspects of an input text and combine these predictions in…
We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare different approaches to decode these multimodal and multilingual fixed-size representations, enabling zero-shot translation between languages and modalities. All our models are trained without the need of cross-modal labeled translation data. Despite a fixed-size representation, we achieve very competitive results on several text and speech translation tasks. In particular, we sig…
Hateful Memes is a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. Difficult examples are added to the dataset to make it hard to rely on unimodal signals, which means only multimodal models can succeed. According to Kiela,the state-of-the-art methods perform poorly compared to humans (64.73% vs. 84.7% accuracy) on Hateful Memes. I propose a new model that combined multimodal with rules, which achieve the first ranking of accuracy and AUROC of 86.8% and 0.923 respectively. These rules are extracted from training set, and focus on improvin…
Eurecat, Centre Tecnològic de Catalunya（加泰罗尼亚技术中心 Eurecat）；Computer Vision Center, Universitat Autònoma de Barcelona（巴塞罗那自治大学计算机视觉中心）
In this work we target the problem of hate speech detection in multimodal publications formed by a text and an image. We gather and annotate a large scale dataset from Twitter, MMHS150K, and propose different models that jointly analyze textual and visual information for hate speech detection, comparing them with unimodal detection. We provide quantitative and qualitative results and analyze the challenges of the proposed task. We find that, even though images are useful for the hate speech detection task, current multimodal models cannot outperform models analyzing only text. We discuss why a…
Alexa AI（亚马逊语音助手人工智能）；National Taiwan University (NTU)（台湾大学）
State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data to generate high-quality synthetic speech. When using reduced amounts of training data, standard TTS models suffer from speech quality and intelligibility degradations, making training low-resource TTS systems problematic. In this paper, we propose a novel extremely low-resource TTS method called Voice Filter that uses as little as one minute of speech from a target speaker. It uses voice conversion (VC) as a post-processing module appended to a pre-existing high-quality TTS system and marks a conceptua…
This paper presents a HMM-based speech recognition engine and its integration into direct manipulation interfaces for Korean document editor. Speech recognition can reduce typical tedious and repetitive actions which are inevitable in standard GUIs (graphic user interfaces). Our system consists of general speech recognition engine called ABrain {Auditory Brain} and speech commandable document editor called SHE {Simple Hearing Editor}. ABrain is a phoneme-based speech recognition engine which shows up to 97% of discrete command recognition rate. SHE is a EuroBridge widget-based document editor …
One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement. Existing work generally ignores the correlation between different speech representations during training, which causes leakage of content information into the speaker representation and thus degrades VC performance. To alleviate this issue, we employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training, to achiev…
Zero-shot cross-lingual transfer learning has been shown to be highly challenging for tasks involving a lot of linguistic specificities or when a cultural gap is present between languages, such as in hate speech detection. In this paper, we highlight this limitation for hate speech detection in several domains and languages using strict experimental settings. Then, we propose to train on multilingual auxiliary tasks -- sentiment analysis, named entity recognition, and tasks relying on syntactic information -- to improve zero-shot transfer of hate speech detection models across languages. We sh…
Bielefeld University（比勒费尔德大学）；University of Bonn（波恩大学）
Memes on the Internet are often harmless and sometimes amusing. However, by using certain types of images, text, or combinations of both, the seemingly harmless meme becomes a multimodal type of hate speech -- a hateful meme. The Hateful Memes Challenge is a first-of-its-kind competition which focuses on detecting hate speech in multimodal memes and it proposes a new data set containing 10,000+ new examples of multimodal content. We utilize VisualBERT -- which meant to be the BERT of vision and language -- that was trained multimodally on images and captions and apply Ensemble Learning. Our ap…
While audio-visual speech models can yield superior performance and robustness compared to audio-only models, their development and adoption are hindered by the lack of labeled and unlabeled audio-visual data and the cost to deploy one model per modality. In this paper, we present u-HuBERT, a self-supervised pre-training framework that can leverage both multimodal and unimodal speech with a unified masked cluster prediction objective. By utilizing modality dropout during pre-training, we demonstrate that a single fine-tuned model can achieve performance on par or better than the state-of-the-a…
Carnegie Mellon University（卡内基梅隆大学）；University of Edinburgh（爱丁堡大学）；University of Copenhagen（哥本哈根大学）
Visual context has been shown to be useful for automatic speech recognition (ASR) systems when the speech signal is noisy or corrupted. Previous work, however, has only demonstrated the utility of visual context in an unrealistic setting, where a fixed set of words are systematically masked in the audio. In this paper, we simulate a more realistic masking scenario during model training, called RandWordMask, where the masking can occur for any word segment. Our experiments on the Flickr 8K Audio Captions Corpus show that multimodal ASR can generalize to recover different types of masked words i…
