Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"speech": models, code, and papers

LEAP System for SRE19 Challenge -- Improvements and Error Analysis

Feb 07, 2020
Shreyas Ramoji, Prashant Krishnan, Bhargavram Mysore, Prachi Singh, Sriram Ganapathy

The NIST Speaker Recognition Evaluation - Conversational Telephone Speech (CTS) challenge 2019 was an open evaluation for the task of speaker verification in challenging conditions. In this paper, we provide a detailed account of the LEAP SRE system submitted to the CTS challenge focusing on the novel components in the back-end system modeling. All the systems used the time-delay neural network (TDNN) based x-vector embeddings. The x-vector system in our SRE19 submission used a large pool of training speakers (about 14k speakers). Following the x-vector extraction, we explored a neural network approach to backend score computation that was optimized for a speaker verification cost. The system combination of generative and neural PLDA models resulted in significant improvements for the SRE evaluation dataset. We also found additional gains for the SRE systems based on score normalization and calibration. Subsequent to the evaluations, we have performed a detailed analysis of the submitted systems. The analysis revealed the incremental gains obtained for different training dataset combinations as well as the modeling methods.

* Submitted to Odyssey 2020, the Speaker and Language Recognition Workshop. Link to GitHub Implementation: 

  Access Paper or Ask Questions

Establishing Human-Robot Trust through Music-Driven Robotic Emotion Prosody and Gesture

Jan 11, 2020
Richard Savery, Ryan Rose, Gil Weinberg

As human-robot collaboration opportunities continue to expand, trust becomes ever more important for full engagement and utilization of robots. Affective trust, built on emotional relationship and interpersonal bonds is particularly critical as it is more resilient to mistakes and increases the willingness to collaborate. In this paper we present a novel model built on music-driven emotional prosody and gestures that encourages the perception of a robotic identity, designed to avoid uncanny valley. Symbolic musical phrases were generated and tagged with emotional information by human musicians. These phrases controlled a synthesis engine playing back pre-rendered audio samples generated through interpolation of phonemes and electronic instruments. Gestures were also driven by the symbolic phrases, encoding the emotion from the musical phrase to low degree-of-freedom movements. Through a user study we showed that our system was able to accurately portray a range of emotions to the user. We also showed with a significant result that our non-linguistic audio generation achieved an 8% higher mean of average trust than using a state-of-the-art text-to-speech system.

* The 28th IEEE International Conference on Robot & Human Interactive Communication 2019 

  Access Paper or Ask Questions

Integrating Dictionary Feature into A Deep Learning Model for Disease Named Entity Recognition

Nov 05, 2019
Hamada A. Nayel, Shashrekha H. L

In recent years, Deep Learning (DL) models are becoming important due to their demonstrated success at overcoming complex learning problems. DL models have been applied effectively for different Natural Language Processing (NLP) tasks such as part-of-Speech (PoS) tagging and Machine Translation (MT). Disease Named Entity Recognition (Disease-NER) is a crucial task which aims at extracting disease Named Entities (NEs) from text. In this paper, a DL model for Disease-NER using dictionary information is proposed and evaluated on National Center for Biotechnology Information (NCBI) disease corpus and BC5CDR dataset. Word embeddings trained over general domain texts as well as biomedical texts have been used to represent input to the proposed model. This study also compares two different Segment Representation (SR) schemes, namely IOB2 and IOBES for Disease-NER. The results illustrate that using dictionary information, pre-trained word embeddings, character embeddings and CRF with global score improves the performance of Disease-NER system.

* 16 pages, 13 figures 

  Access Paper or Ask Questions

Contextual Joint Factor Acoustic Embeddings

Oct 16, 2019
Yanpei Shi, Qiang Huang, Thomas Hain

Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. We propose two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic context. The first approach is a contextual joint factor synthesis encoder, where the encoder in an encoder/decoder framework is trained to extract joint factors from surrounding audio frames to best generate the target output. The second approach is a contextual joint factor analysis encoder, where the encoder is trained to analyse joint factors from the source signal that correlates best with the neighbouring audio. To evaluate the effectiveness of our approaches compared to prior work, we chose two tasks - phone classification and speaker recognition - and test on different TIMIT data sets. Experimental results show that one of our proposed approaches outperforms phone classification baselines, yielding a classification accuracy of 74.1%. When using additional out-of-domain data for training, an additional 2-3% improvements can be obtained, for both for phone classification and speaker recognition tasks.

  Access Paper or Ask Questions

Named Entity Recognition Only from Word Embeddings

Aug 31, 2019
Ying Luo, Hai Zhao, Junlang Zhan

Deep neural network models have helped named entity (NE) recognition achieve amazing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Efforts have been made to replace human annotations with external knowledge (e.g., NE dictionary, part-of-speech tags), while it is another challenge to obtain such effective resources. In this work, we propose a fully unsupervised NE recognition model which only needs to take informative clues from pre-trained word embeddings. We first apply Gaussian Hidden Markov Model and Deep Autoencoding Gaussian Mixture Model on word embeddings for entity span detection and type prediction, and then further design an instance selector based on reinforcement learning to distinguish positive sentences from noisy sentences and refine these coarse-grained annotations through neural networks. Extensive experiments on CoNLL benchmark datasets demonstrate that our proposed light NE recognition model achieves remarkable performance without using any annotated lexicon or corpus.

  Access Paper or Ask Questions

Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model

Aug 29, 2019
Yoshiaki Bando, Yoko Sasaki, Kazuyoshi Yoshii

This paper presents an unsupervised method that trains neural source separation by using only multichannel mixture signals. Conventional neural separation methods require a lot of supervised data to achieve excellent performance. Although multichannel methods based on spatial information can work without such training data, they are often sensitive to parameter initialization and degraded with the sources located close to each other. The proposed method uses a cost function based on a spatial model called a complex Gaussian mixture model (cGMM). This model has the time-frequency (TF) masks and direction of arrivals (DoAs) of sources as latent variables and is used for training separation and localization networks that respectively estimate these variables. This joint training solves the frequency permutation ambiguity of the spatial model in a unified deep Bayesian framework. In addition, the pre-trained network can be used not only for conducting monaural separation but also for efficiently initializing a multichannel separation algorithm. Experimental results with simulated speech mixtures showed that our method outperformed a conventional initialization method.

* 6 pages, 2 figures, accepted for publication in 2019 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 

  Access Paper or Ask Questions

Spatial Pyramid Encoding with Convex Length Normalization for Text-Independent Speaker Verification

Jun 19, 2019
Youngmoon Jung, Younggwan Kim, Hyungjun Lim, Yeunju Choi, Hoirin Kim

In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition the output feature maps from a deep residual network (ResNet) into increasingly fine sub-regions and extract speaker embeddings from each sub-region through a learnable dictionary encoding layer. These embeddings are concatenated to obtain the final speaker representation. The SPE layer not only generates a fixed-dimensional speaker embedding for a variable-length speech segment, but also aggregates the information of feature distribution from multi-level temporal bins. Furthermore, we apply deep length normalization by augmenting the loss function with ring loss. By applying ring loss, the network gradually learns to normalize the speaker embeddings using model weights themselves while preserving convexity, leading to more robust speaker embeddings. Experiments on the VoxCeleb1 dataset show that the proposed system using the SPE layer and ring loss-based deep length normalization outperforms both i-vector and d-vector baselines.

* 5 pages, 2 figures, Interspeech 2019 

  Access Paper or Ask Questions

Arabic Text Diacritization Using Deep Neural Networks

Apr 25, 2019
Ali Fadel, Ibraheem Tuffaha, Bara' Al-Jawarneh, Mahmoud Al-Ayyoub

Diacritization of Arabic text is both an interesting and a challenging problem at the same time with various applications ranging from speech synthesis to helping students learning the Arabic language. Like many other tasks or problems in Arabic language processing, the weak efforts invested into this problem and the lack of available (open-source) resources hinder the progress towards solving this problem. This work provides a critical review for the currently existing systems, measures and resources for Arabic text diacritization. Moreover, it introduces a much-needed free-for-all cleaned dataset that can be easily used to benchmark any work on Arabic diacritization. Extracted from the Tashkeela Corpus, the dataset consists of 55K lines containing about 2.3M words. After constructing the dataset, existing tools and systems are tested on it. The results of the experiments show that the neural Shakkala system significantly outperforms traditional rule-based approaches and other closed-source tools with a Diacritic Error Rate (DER) of 2.88% compared with 13.78%, which the best DER for the non-neural approach (obtained by the Mishkal tool).

* 7 pages, 4 figures, 15 tables 

  Access Paper or Ask Questions

Speaker Adaptation for End-to-End CTC Models

Jan 04, 2019
Ke Li, Jinyu Li, Yong Zhao, Kshitiz Kumar, Yifan Gong

We propose two approaches for speaker adaptation in end-to-end (E2E) automatic speech recognition systems. One is Kullback-Leibler divergence (KLD) regularization and the other is multi-task learning (MTL). Both approaches aim to address the data sparsity especially output target sparsity issue of speaker adaptation in E2E systems. The KLD regularization adapts a model by forcing the output distribution from the adapted model to be close to the unadapted one. The MTL utilizes a jointly trained auxiliary task to improve the performance of the main task. We investigated our approaches on E2E connectionist temporal classification (CTC) models with three different types of output units. Experiments on the Microsoft short message dictation task demonstrated that MTL outperforms KLD regularization. In particular, the MTL adaptation obtained 8.8\% and 4.0\% relative word error rate reductions (WERRs) for supervised and unsupervised adaptations for the word CTC model, and 9.6% and 3.8% relative WERRs for the mix-unit CTC model, respectively.

* published at IEEE Workshop of Spoken Language Technology 

  Access Paper or Ask Questions

Distill-Net: Application-Specific Distillation of Deep Convolutional Neural Networks for Resource-Constrained IoT Platforms

Dec 16, 2018
Mohammad Motamedi, Felix Portillo, Daniel Fong, Soheil Ghiasi

Many Internet-of-Things (IoT) applications demand fast and accurate understanding of a few key events in their surrounding environment. Deep Convolutional Neural Networks (CNNs) have emerged as an effective approach to understand speech, images, and similar high dimensional data types. Algorithmic performance of modern CNNs, however, fundamentally relies on learning class-agnostic hierarchical features that only exist in comprehensive training datasets with many classes. As a result, fast inference using CNNs trained on such datasets is prohibitive for most resource-constrained IoT platforms. To bridge this gap, we present a principled and practical methodology for distilling a complex modern CNN that is trained to effectively recognize many different classes of input data into an application-dependent essential core that not only recognizes the few classes of interest to the application accurately, but also runs efficiently on platforms with limited resources. Experimental results confirm that our approach strikes a favorable balance between classification accuracy (application constraint), inference efficiency (platform constraint), and productive development of new applications (business constraint).

  Access Paper or Ask Questions