The Experts below are selected from a list of 5496 Experts worldwide ranked by ideXlab platform

Hungyi Lee - One of the best experts on this subject based on the ideXlab platform.

  • language transfer of Audio word2vec learning Audio Segment representations without target language data
    International Conference on Acoustics Speech and Signal Processing, 2018
    Co-Authors: Chiahao Shen, Janet Y Sung, Hungyi Lee
    Abstract:

    Audio Word2Vec offers vector representations of fixed dimensionality for variable-length Audio Segments using Sequence to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the Audio Segments to a good degree, with real world applications such as spoken term detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the Audio Segments of another language (target language). We found that SA can still catch the phonetic structure from the Audio Segments of the target language if the source and target languages are similar. In STD, we obtain the vector representations from the SA learned from a large amount of source language data, and found them surpass the representations from naive encoder and SA directly learned from a small amount of target language data. The result shows that it is possible to learn Audio Word2Vec model from high-resource languages and use it on low-resource languages. This further expands the usability of Audio Word2Vec.

  • language transfer of Audio word2vec learning Audio Segment representations without target language data
    arXiv: Computation and Language, 2017
    Co-Authors: Chiahao Shen, Janet Y Sung, Hungyi Lee
    Abstract:

    Audio Word2Vec offers vector representations of fixed dimensionality for variable-length Audio Segments using Sequence-to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the Audio Segments to a good degree, with real world applications such as query-by-example Spoken Term Detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the Audio Segments of another language (target language). We found that SA can still catch phonetic structure from the Audio Segments of the target language if the source and target languages are similar. In query-by-example STD, we obtain the vector representations from the SA learned from a large amount of source language data, and found them surpass the representations from naive encoder and SA directly learned from a small amount of target language data. The result shows that it is possible to learn Audio Word2Vec model from high-resource languages and use it on low-resource languages. This further expands the usability of Audio Word2Vec.

  • Audio word2vec unsupervised learning of Audio Segment representations using sequence to sequence autoencoder
    arXiv: Sound, 2016
    Co-Authors: Yuan Chung, Chiahao Shen, Hungyi Lee, Linshan Lee
    Abstract:

    The vector representations of fixed dimensionality for words (in text) offered by Word2Vec have been shown to be very useful in many application scenarios, in particular due to the semantic information they carry. This paper proposes a parallel version, the Audio Word2Vec. It offers the vector representations of fixed dimensionality for variable-length Audio Segments. These vector representations are shown to describe the sequential phonetic structures of the Audio Segments to a good degree, with very attractive real world applications such as query-by-example Spoken Term Detection (STD). In this STD application, the proposed approach significantly outperformed the conventional Dynamic Time Warping (DTW) based approaches at significantly lower computation requirements. We propose unsupervised learning of Audio Word2Vec from Audio data without human annotation using Sequence-to-sequence Audoencoder (SA). SA consists of two RNNs equipped with Long Short-Term Memory (LSTM) units: the first RNN (encoder) maps the input Audio sequence into a vector representation of fixed dimensionality, and the second RNN (decoder) maps the representation back to the input Audio sequence. The two RNNs are jointly trained by minimizing the reconstruction error. Denoising Sequence-to-sequence Autoencoder (DSA) is furthered proposed offering more robust learning.

Chiahao Shen - One of the best experts on this subject based on the ideXlab platform.

  • language transfer of Audio word2vec learning Audio Segment representations without target language data
    International Conference on Acoustics Speech and Signal Processing, 2018
    Co-Authors: Chiahao Shen, Janet Y Sung, Hungyi Lee
    Abstract:

    Audio Word2Vec offers vector representations of fixed dimensionality for variable-length Audio Segments using Sequence to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the Audio Segments to a good degree, with real world applications such as spoken term detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the Audio Segments of another language (target language). We found that SA can still catch the phonetic structure from the Audio Segments of the target language if the source and target languages are similar. In STD, we obtain the vector representations from the SA learned from a large amount of source language data, and found them surpass the representations from naive encoder and SA directly learned from a small amount of target language data. The result shows that it is possible to learn Audio Word2Vec model from high-resource languages and use it on low-resource languages. This further expands the usability of Audio Word2Vec.

  • language transfer of Audio word2vec learning Audio Segment representations without target language data
    arXiv: Computation and Language, 2017
    Co-Authors: Chiahao Shen, Janet Y Sung, Hungyi Lee
    Abstract:

    Audio Word2Vec offers vector representations of fixed dimensionality for variable-length Audio Segments using Sequence-to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the Audio Segments to a good degree, with real world applications such as query-by-example Spoken Term Detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the Audio Segments of another language (target language). We found that SA can still catch phonetic structure from the Audio Segments of the target language if the source and target languages are similar. In query-by-example STD, we obtain the vector representations from the SA learned from a large amount of source language data, and found them surpass the representations from naive encoder and SA directly learned from a small amount of target language data. The result shows that it is possible to learn Audio Word2Vec model from high-resource languages and use it on low-resource languages. This further expands the usability of Audio Word2Vec.

  • Audio word2vec unsupervised learning of Audio Segment representations using sequence to sequence autoencoder
    arXiv: Sound, 2016
    Co-Authors: Yuan Chung, Chiahao Shen, Hungyi Lee, Linshan Lee
    Abstract:

    The vector representations of fixed dimensionality for words (in text) offered by Word2Vec have been shown to be very useful in many application scenarios, in particular due to the semantic information they carry. This paper proposes a parallel version, the Audio Word2Vec. It offers the vector representations of fixed dimensionality for variable-length Audio Segments. These vector representations are shown to describe the sequential phonetic structures of the Audio Segments to a good degree, with very attractive real world applications such as query-by-example Spoken Term Detection (STD). In this STD application, the proposed approach significantly outperformed the conventional Dynamic Time Warping (DTW) based approaches at significantly lower computation requirements. We propose unsupervised learning of Audio Word2Vec from Audio data without human annotation using Sequence-to-sequence Audoencoder (SA). SA consists of two RNNs equipped with Long Short-Term Memory (LSTM) units: the first RNN (encoder) maps the input Audio sequence into a vector representation of fixed dimensionality, and the second RNN (decoder) maps the representation back to the input Audio sequence. The two RNNs are jointly trained by minimizing the reconstruction error. Denoising Sequence-to-sequence Autoencoder (DSA) is furthered proposed offering more robust learning.

Janet Y Sung - One of the best experts on this subject based on the ideXlab platform.

  • language transfer of Audio word2vec learning Audio Segment representations without target language data
    International Conference on Acoustics Speech and Signal Processing, 2018
    Co-Authors: Chiahao Shen, Janet Y Sung, Hungyi Lee
    Abstract:

    Audio Word2Vec offers vector representations of fixed dimensionality for variable-length Audio Segments using Sequence to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the Audio Segments to a good degree, with real world applications such as spoken term detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the Audio Segments of another language (target language). We found that SA can still catch the phonetic structure from the Audio Segments of the target language if the source and target languages are similar. In STD, we obtain the vector representations from the SA learned from a large amount of source language data, and found them surpass the representations from naive encoder and SA directly learned from a small amount of target language data. The result shows that it is possible to learn Audio Word2Vec model from high-resource languages and use it on low-resource languages. This further expands the usability of Audio Word2Vec.

  • language transfer of Audio word2vec learning Audio Segment representations without target language data
    arXiv: Computation and Language, 2017
    Co-Authors: Chiahao Shen, Janet Y Sung, Hungyi Lee
    Abstract:

    Audio Word2Vec offers vector representations of fixed dimensionality for variable-length Audio Segments using Sequence-to-sequence Autoencoder (SA). These vector representations are shown to describe the sequential phonetic structures of the Audio Segments to a good degree, with real world applications such as query-by-example Spoken Term Detection (STD). This paper examines the capability of language transfer of Audio Word2Vec. We train SA from one language (source language) and use it to extract the vector representation of the Audio Segments of another language (target language). We found that SA can still catch phonetic structure from the Audio Segments of the target language if the source and target languages are similar. In query-by-example STD, we obtain the vector representations from the SA learned from a large amount of source language data, and found them surpass the representations from naive encoder and SA directly learned from a small amount of target language data. The result shows that it is possible to learn Audio Word2Vec model from high-resource languages and use it on low-resource languages. This further expands the usability of Audio Word2Vec.

John Bridle - One of the best experts on this subject based on the ideXlab platform.

  • multi task learning for voice trigger detection
    International Conference on Acoustics Speech and Signal Processing, 2020
    Co-Authors: Siddharth Sigtia, Pascal Clark, Rob Haynes, Hywel Richards, John Bridle
    Abstract:

    We describe the design of a voice trigger detection system for smart speakers. In this study, we address two major challenges. The first is that the detectors are deployed in complex acoustic environments with external noise and loud playback by the device itself. Secondly, collecting training examples for a specific keyword or trigger phrase is challenging resulting in a scarcity of trigger phrase specific training data. We describe a two-stage cascaded architecture where a low-power detector is always running and listening for the trigger phrase. If a detection is made at this stage, the candidate Audio Segment is re-scored by larger, more complex models to verify that the Segment contains the trigger phrase. In this study, we focus our attention on the architecture and design of these second-pass detectors. We start by training a general acoustic model that produces phonetic transcriptions given a large labelled training dataset. Next, we collect a much smaller dataset of examples that are challenging for the baseline system. We then use multi-task learning to train a model to simultaneously produce accurate phonetic transcriptions on the larger dataset and discriminate between true and easily confusable examples using the smaller dataset. Our results demonstrate that the proposed model reduces errors by half compared to the baseline in a range of challenging test conditions without requiring extra parameters.

Iynkaran Natgunanathan - One of the best experts on this subject based on the ideXlab platform.

  • Spread spectrum-based high embedding capacity watermarking method for Audio signals
    IEEE Transactions on Audio Speech and Language Processing, 2015
    Co-Authors: Yong Xiang, Yue Rong, Iynkaran Natgunanathan, Song Guo
    Abstract:

    Audio watermarking is a promising technology for copyright protection of Audio data. Built upon the concept of spread spectrum (SS), many SS-based Audio watermarking methods have been developed, where a pseudonoise (PN) sequence is usually used to introduce security. A major drawback of the existing SS-based Audio watermarking methods is their low embedding capacity. In this paper, we propose a new SS-based Audio watermarking method which possesses much higher embedding capacity while ensuring satisfactory imperceptibility and robustness. The high embedding capacity is achieved through a set of mechanisms: embedding multiple watermark bits in one Audio Segment, reducing host signal interference on watermark extraction, and adaptively adjusting PN sequence amplitude in watermark embedding based on the property of Audio Segments. The effectiveness of the proposed Audio watermarking method is demonstrated by simulation examples.

  • robust patchwork based embedding and decoding scheme for digital Audio watermarking
    IEEE Transactions on Audio Speech and Language Processing, 2012
    Co-Authors: Iynkaran Natgunanathan, Yue Rong, Yong Xiang, Wanlei Zhou
    Abstract:

    This paper presents a novel patchwork-based embedding and decoding scheme for digital Audio watermarking. At the embedding stage, an Audio Segment is divided into two subSegments and the discrete cosine transform (DCT) coefficients of the subSegments are computed. The DCT coefficients related to a specified frequency region are then partitioned into a number of frame pairs. The DCT frame pairs suitable for watermark embedding are chosen by a selection criterion and watermarks are embedded into the selected DCT frame pairs by modifying their coefficients, controlled by a secret key. The modifications are conducted in such a way that the selection criterion used at the embedding stage can be applied at the decoding stage to identify the watermarked DCT frame pairs. At the decoding stage, the secret key is utilized to extract watermarks from the watermarked DCT frame pairs. Compared with existing patchwork watermarking methods, the proposed scheme does not require information of which frame pairs of the watermarked Audio signal enclose watermarks and is more robust to conventional attacks.