Naoya Takahashi

Kazuki Shimada, Archontis Politis, Parthasaarathy Sudarsanam et al.

While direction of arrival (DOA) of sound events is generally estimated from multichannel audio data recorded in a microphone array, sound events usually derive from visually perceptible source objects, e.g., sounds of footsteps come from the feet of a walker. This paper proposes an audio-visual sound event localization and detection (SELD) task, which uses multichannel audio and video information to estimate the temporal activation and DOA of target sound events. Audio-visual SELD systems can detect and localize sound events using signals from a microphone array and audio-visual correspondence. We also introduce an audio-visual dataset, Sony-TAu Realistic Spatial Soundscapes 2023 (STARSS23), which consists of multichannel audio data recorded with a microphone array, video data, and spatiotemporal annotation of sound events. Sound scenes in STARSS23 are recorded with instructions, which guide recording participants to ensure adequate activity and occurrences of sound events. STARSS23 also serves human-annotated temporal activation labels and human-confirmed DOA labels, which are based on tracking results of a motion capture system. Our benchmark results demonstrate the benefits of using visual object positions in audio-visual SELD tasks. The data is available at https://zenodo.org/record/7880637.

Shrutina Agarwal, Sriram Ganapathy, Naoya Takahashi · deepmind

In this paper, we propose a model to perform style transfer of speech to singing voice. Contrary to the previous signal processing-based methods, which require high-quality singing templates or phoneme synchronization, we explore a data-driven approach for the problem of converting natural speech to singing voice. We develop a novel neural network architecture, called SymNet, which models the alignment of the input speech with the target melody while preserving the speaker identity and naturalness. The proposed SymNet model is comprised of symmetrical stack of three types of layers - convolutional, transformer, and self-attention layers. The paper also explores novel data augmentation and generative loss annealing methods to facilitate the model training. Experiments are performed on the NUS and NHSS datasets which consist of parallel data of speech and singing voice. In these experiments, we show that the proposed SymNet model improves the objective reconstruction quality significantly over the previously published methods and baseline architectures. Further, a subjective listening test confirms the improved quality of the audio obtained using the proposed approach (absolute improvement of 0.37 in mean opinion score measure over the baseline system).

Hao-Wen Dong, Naoya Takahashi, Yuki Mitsufuji et al.

Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound separation has investigated separating a target sound out of an audio mixture given a text query. Such text-queried sound separation systems provide a natural and scalable interface for specifying arbitrary target sounds. However, supervised text-queried sound separation systems require costly labeled audio-text pairs for training. Moreover, the audio provided in existing datasets is often recorded in a controlled environment, causing a considerable generalization gap to noisy audio in the wild. In this work, we aim to approach text-queried universal sound separation by using only unlabeled data. We propose to leverage the visual modality as a bridge to learn the desired audio-textual correspondence. The proposed CLIPSep model first encodes the input query into a query vector using the contrastive language-image pretraining (CLIP) model, and the query vector is then used to condition an audio separation model to separate out the target sound. While the model is trained on image-audio pairs extracted from unlabeled videos, at test time we can instead query the model with text inputs in a zero-shot setting, thanks to the joint language-image embedding learned by the CLIP model. Further, videos in the wild often contain off-screen sounds and background noise that may hinder the model from learning the desired audio-textual correspondence. To address this problem, we further propose an approach called noise invariant training for training a query-based sound separation model on noisy data. Experimental results show that the proposed models successfully learn text-queried universal sound separation using only noisy unlabeled videos, even achieving competitive performance against a supervised model in some settings.

Kin Wai Cheuk, Ryosuke Sawata, Toshimitsu Uesaka et al.

In this paper we propose a novel generative approach, DiffRoll, to tackle automatic music transcription (AMT). Instead of treating AMT as a discriminative task in which the model is trained to convert spectrograms into piano rolls, we think of it as a conditional generative task where we train our model to generate realistic looking piano rolls from pure Gaussian noise conditioned on spectrograms. This new AMT formulation enables DiffRoll to transcribe, generate and even inpaint music. Due to the classifier-free nature, DiffRoll is also able to be trained on unpaired datasets where only piano rolls are available. Our experiments show that DiffRoll outperforms its discriminative counterpart by 19 percentage points (ppt.) and our ablation studies also indicate that it outperforms similar existing methods by 4.8 ppt. Source code and demonstration are available https://sony.github.io/DiffRoll/.

Naoya Takahashi, Mayank Kumar, Singh et al.

Recent progress in deep generative models has improved the quality of neural vocoders in speech domain. However, generating a high-quality singing voice remains challenging due to a wider variety of musical expressions in pitch, loudness, and pronunciations. In this work, we propose a hierarchical diffusion model for singing voice neural vocoders. The proposed method consists of multiple diffusion models operating in different sampling rates; the model at the lowest sampling rate focuses on generating accurate low-frequency components such as pitch, and other models progressively generate the waveform at higher sampling rates on the basis of the data at the lower sampling rate and acoustic features. Experimental results show that the proposed method produces high-quality singing voices for multiple singers, outperforming state-of-the-art neural vocoders with a similar range of computational costs.

Nirmesh Shah, Mayank Kumar Singh, Naoya Takahashi et al.

Primary goal of an emotional voice conversion (EVC) system is to convert the emotion of a given speech signal from one style to another style without modifying the linguistic content of the signal. Most of the state-of-the-art approaches convert emotions for seen speaker-emotion combinations only. In this paper, we tackle the problem of converting the emotion of speakers whose only neutral data are present during the time of training and testing (i.e., unseen speaker-emotion combinations). To this end, we extend a recently proposed StartGANv2-VC architecture by utilizing dual encoders for learning the speaker and emotion style embeddings separately along with dual domain source classifiers. For achieving the conversion to unseen speaker-emotion combinations, we propose a Virtual Domain Pairing (VDP) training strategy, which virtually incorporates the speaker-emotion pairs that are not present in the real data without compromising the min-max game of a discriminator and generator in adversarial training. We evaluate the proposed method using a Hindi emotional database.

Naoya Takahashi, Mayank Kumar Singh, Yuki Mitsufuji

Recent progress in deep generative models has improved the quality of voice conversion in the speech domain. However, high-quality singing voice conversion (SVC) of unseen singers remains challenging due to the wider variety of musical expressions in pitch, loudness, and pronunciation. Moreover, singing voices are often recorded with reverb and accompaniment music, which make SVC even more challenging. In this work, we present a robust one-shot SVC (ROSVC) that performs any-to-any SVC robustly even on such distorted singing voices. To this end, we first propose a one-shot SVC model based on generative adversarial networks that generalizes to unseen singers via partial domain conditioning and learns to accurately recover the target pitch via pitch distribution matching and AdaIN-skip conditioning. We then propose a two-stage training method called Robustify that train the one-shot SVC model in the first stage on clean data to ensure high-quality conversion, and introduces enhancement modules to the encoders of the model in the second stage to enhance the feature extraction from distorted singing voices. To further improve the voice quality and pitch reconstruction accuracy, we finally propose a hierarchical diffusion model for singing voice neural vocoders. Experimental results show that the proposed method outperforms state-of-the-art one-shot SVC baselines for both seen and unseen singers and significantly improves the robustness against distortions.

Naoya Takahashi, Mayank K. Singh, Yuki Mitsufuji

Image-to-image translation and voice conversion enable the generation of a new facial image and voice while maintaining some of the semantics such as a pose in an image and linguistic content in audio, respectively. They can aid in the content-creation process in many applications. However, as they are limited to the conversion within each modality, matching the impression of the generated face and voice remains an open question. We propose a cross-modal style transfer framework called XFaVoT that jointly learns four tasks: image translation and voice conversion tasks with audio or image guidance, which enables the generation of ``face that matches given voice" and ``voice that matches given face", and intra-modality translation tasks with a single framework. Experimental results on multiple datasets show that XFaVoT achieves cross-modal style translation of image and voice, outperforming baselines in terms of quality, diversity, and face-voice correspondence.

Kazuki Shimada, Archontis Politis, Iran R. Roman et al.

This paper presents the objective, dataset, baseline, and metrics of Task 3 of the DCASE2025 Challenge on sound event localization and detection (SELD). In previous editions, the challenge used four-channel audio formats of first-order Ambisonics (FOA) and microphone array. In contrast, this year's challenge investigates SELD with stereo audio data (termed stereo SELD). This change shifts the focus from more specialized 360° audio and audiovisual scene analysis to more commonplace audio and media scenarios with limited field-of-view (FOV). Due to inherent angular ambiguities in stereo audio data, the task focuses on direction-of-arrival (DOA) estimation in the azimuth plane (left-right axis) along with distance estimation. The challenge remains divided into two tracks: audio-only and audiovisual, with the audiovisual track introducing a new sub-task of onscreen/offscreen event classification necessitated by the limited FOV. This challenge introduces the DCASE2025 Task3 Stereo SELD Dataset, whose stereo audio and perspective video clips are sampled and converted from the STARSS23 recordings. The baseline system is designed to process stereo audio and corresponding video frames as inputs. In addition to the typical SELD event classification and localization, it integrates onscreen/offscreen classification for the audiovisual track. The evaluation metrics have been modified to introduce an onscreen/offscreen accuracy metric, which assesses the models' ability to identify which sound sources are onscreen. In the experimental evaluation, the baseline system performs reasonably well with the stereo audio data.

Mayank Kumar Singh, Naoya Takahashi, Onoe Naoyuki

Many existing works on voice conversion (VC) tasks use automatic speech recognition (ASR) models for ensuring linguistic consistency between source and converted samples. However, for the low-data resource domains, training a high-quality ASR remains to be a challenging task. In this work, we propose a novel iterative way of improving both the ASR and VC models. We first train an ASR model which is used to ensure content preservation while training a VC model. In the next iteration, the VC model is used as a data augmentation method to further fine-tune the ASR model and generalize it to diverse speakers. By iteratively leveraging the improved ASR model to train VC model and vice-versa, we experimentally show improvement in both the models. Our proposed framework outperforms the ASR and one-shot VC baseline models on English singing and Hindi speech domains in subjective and objective evaluations in low-data resource settings.

Kazuki Shimada, Yuichiro Koyama, Shusuke Takahashi et al.

Sound event localization and detection (SELD) involves identifying the direction-of-arrival (DOA) and the event class. The SELD methods with a class-wise output format make the model predict activities of all sound event classes and corresponding locations. The class-wise methods can output activity-coupled Cartesian DOA (ACCDOA) vectors, which enable us to solve a SELD task with a single target using a single network. However, there is still a challenge in detecting the same event class from multiple locations. To overcome this problem while maintaining the advantages of the class-wise format, we extended ACCDOA to a multi one and proposed auxiliary duplicating permutation invariant training (ADPIT). The multi- ACCDOA format (a class- and track-wise output format) enables the model to solve the cases with overlaps from the same class. The class-wise ADPIT scheme enables each track of the multi-ACCDOA format to learn with the same target as the single-ACCDOA format. In evaluations with the DCASE 2021 Task 3 dataset, the model trained with the multi-ACCDOA format and with the class-wise ADPIT detects overlapping events from the same class while maintaining its performance in the other cases. Also, the proposed method performed comparably to state-of-the-art SELD methods with fewer parameters.

Yuichiro Koyama, Kazuhide Shigemi, Masafumi Takahashi et al.

Recording and annotating real sound events for a sound event localization and detection (SELD) task is time consuming, and data augmentation techniques are often favored when the amount of data is limited. However, how to augment the spatial information in a dataset, including unlabeled directional interference events, remains an open research question. Furthermore, directional interference events make it difficult to accurately extract spatial characteristics from target sound events. To address this problem, we propose an impulse response simulation framework (IRS) that augments spatial characteristics using simulated room impulse responses (RIR). RIRs corresponding to a microphone array assumed to be placed in various rooms are accurately simulated, and the source signals of the target sound events are extracted from a mixture. The simulated RIRs are then convolved with the extracted source signals to obtain an augmented multi-channel training dataset. Evaluation results obtained using the TAU-NIGENS Spatial Sound Events 2021 dataset show that the IRS contributes to improving the overall SELD performance. Additionally, we conducted an ablation study to discuss the contribution and need for each component within the IRS.

Naoya Takahashi, Yuki Mitsufuji

This paper deals with the problem of informed source separation (ISS), where the sources are accessible during the so-called \textit{encoding} stage. Previous works computed side-information during the encoding stage and source separation models were designed to utilize the side-information to improve the separation performance. In contrast, in this work, we improve the performance of a pretrained separation model that does not use any side-information. To this end, we propose to adopt an adversarial attack for the opposite purpose, i.e., rather than computing the perturbation to degrade the separation, we compute an imperceptible perturbation called amicable noise to improve the separation. Experimental results show that the proposed approach selectively improves the performance of the targeted separation model by 2.23 dB on average and is robust to signal compression. Moreover, we propose multi-model multi-purpose learning that control the effect of the perturbation on different models individually.

Naoya Takahashi, Mayank Kumar Singh, Yuki Mitsufuji

Audio steganography aims at concealing secret information in carrier audio with imperceptible modification on the carrier. Although previous works addressed the robustness of concealed message recovery against distortions introduced during transmission, they do not address the robustness against aggressive editing such as mixing of other audio sources and source separation. In this work, we propose for the first time a steganography method that can embed information into individual sound sources in a mixture such as instrumental tracks in music. To this end, we propose a time-domain model and curriculum learning essential to learn to decode the concealed message from the separated sources. Experimental results show that the proposed method successfully conceals the information in an imperceptible perturbation and that the information can be correctly recovered even after mixing of other sources and separation by a source separation algorithm. Furthermore, we show that the proposed method can be applied to multiple sources simultaneously without interfering with the decoder for other sources even after the sources are mixed and separated.

Kazuki Shimada, Naoya Takahashi, Yuichiro Koyama et al.

This report describes our systems submitted to the DCASE2021 challenge task 3: sound event localization and detection (SELD) with directional interference. Our previous system based on activity-coupled Cartesian direction of arrival (ACCDOA) representation enables us to solve a SELD task with a single target. This ACCDOA-based system with efficient network architecture called RD3Net and data augmentation techniques outperformed state-of-the-art SELD systems in terms of localization and location-dependent detection. Using the ACCDOA-based system as a base, we perform model ensembles by averaging outputs of several systems trained with different conditions such as input features, training folds, and model architectures. We also use the event independent network v2 (EINV2)-based system to increase the diversity of the model ensembles. To generalize the models, we further propose impulse response simulation (IRS), which generates simulated multi-channel signals by convolving simulated room impulse responses (RIRs) with source signals extracted from the original dataset. Our systems significantly improved over the baseline system on the development dataset.

Sakya Basak, Shrutina Agarwal, Sriram Ganapathy et al.

Automatic transcription of monophonic/polyphonic music is a challenging task due to the lack of availability of large amounts of transcribed data. In this paper, we propose a data augmentation method that converts natural speech to singing voice based on vocoder based speech synthesizer. This approach, called voice to singing (V2S), performs the voice style conversion by modulating the F0 contour of the natural speech with that of a singing voice. The V2S model based style transfer can generate good quality singing voice thereby enabling the conversion of large corpora of natural speech to singing voice that is useful in building an E2E lyrics transcription system. In our experiments on monophonic singing voice data, the V2S style transfer provides a significant gain (relative improvements of 21%) for the E2E lyrics transcription system. We also discuss additional components like transfer learning and lyrics based language modeling to improve the performance of the lyrics transcription system.

Naoya Takahashi, Mayank Kumar Singh, Yuki Mitsufuji

Conventional singing voice conversion (SVC) methods often suffer from operating in high-resolution audio owing to a high dimensionality of data. In this paper, we propose a hierarchical representation learning that enables the learning of disentangled representations with multiple resolutions independently. With the learned disentangled representations, the proposed method progressively performs SVC from low to high resolutions. Experimental results show that the proposed method outperforms baselines that operate with a single resolution in terms of mean opinion score (MOS), similarity score, and pitch accuracy.

Naoya Takahashi, Yuki Mitsufuji

Tasks that involve high-resolution dense prediction require a modeling of both local and global patterns in a large input field. Although the local and global structures often depend on each other and their simultaneous modeling is important, many convolutional neural network (CNN)-based approaches interchange representations in different resolutions only a few times. In this paper, we claim the importance of a dense simultaneous modeling of multiresolution representation and propose a novel CNN architecture called densely connected multidilated DenseNet (D3Net). D3Net involves a novel multidilated convolution that has different dilation factors in a single layer to model different resolutions simultaneously. By combining the multidilated convolution with the DenseNet architecture, D3Net incorporates multiresolution learning with an exponentially growing receptive field in almost all layers, while avoiding the aliasing problem that occurs when we naively incorporate the dilated convolution in DenseNet. Experiments on the image semantic segmentation task using Cityscapes and the audio source separation task using MUSDB18 show that the proposed method has superior performance over state-of-the-art methods.

Kazuki Shimada, Yuichiro Koyama, Naoya Takahashi et al.

Neural-network (NN)-based methods show high performance in sound event localization and detection (SELD). Conventional NN-based methods use two branches for a sound event detection (SED) target and a direction-of-arrival (DOA) target. The two-branch representation with a single network has to decide how to balance the two objectives during optimization. Using two networks dedicated to each task increases system complexity and network size. To address these problems, we propose an activity-coupled Cartesian DOA (ACCDOA) representation, which assigns a sound event activity to the length of a corresponding Cartesian DOA vector. The ACCDOA representation enables us to solve a SELD task with a single target and has two advantages: avoiding the necessity of balancing the objectives and model size increase. In experimental evaluations with the DCASE 2020 Task 3 dataset, the ACCDOA representation outperformed the two-branch representation in SELD metrics with a smaller network size. The ACCDOA-based SELD system also performed better than state-of-the-art SELD systems in terms of localization and location-dependent detection.

Naoya Takahashi, Shota Inoue, Yuki Mitsufuji

Despite the excellent performance of neural-network-based audio source separation methods and their wide range of applications, their robustness against intentional attacks has been largely neglected. In this work, we reformulate various adversarial attack methods for the audio source separation problem and intensively investigate them under different attack conditions and target models. We further propose a simple yet effective regularization method to obtain imperceptible adversarial noise while maximizing the impact on separation quality with low computational complexity. Experimental results show that it is possible to largely degrade the separation quality by adding imperceptibly small noise when the noise is crafted for the target model. We also show the robustness of source separation models against a black-box attack. This study provides potentially useful insights for developing content protection methods against the abuse of separated signals and improving the separation performance and robustness.

Naoya Takahashi, Yuki Mitsufuji

Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the large input field modeling using sequentially down- and up-sampling feature maps or dilated convolution. In this paper, we claim the importance of a rapid growth of a receptive field and a simultaneous modeling of multi-resolution data in a single convolution layer, and propose a novel CNN architecture called densely connected dilated DenseNet (D3Net). D3Net involves a novel multi-dilated convolution that has different dilation factors in a single layer to model different resolutions simultaneously. By combining the multi-dilated convolution with DenseNet architecture, D3Net avoids the aliasing problem that exists when we naively incorporate the dilated convolution in DenseNet. Experimental results on MUSDB18 dataset show that D3Net achieves state-of-the-art performance with an average signal to distortion ratio (SDR) of 6.01 dB.

Kazuki Shimada, Naoya Takahashi, Shusuke Takahashi et al.

Our systems submitted to the DCASE2020 task~3: Sound Event Localization and Detection (SELD) are described in this report. We consider two systems: a single-stage system that solve sound event localization~(SEL) and sound event detection~(SED) simultaneously, and a two-stage system that first handles the SED and SEL tasks individually and later combines those results. As the single-stage system, we propose a unified training framework that uses an activity-coupled Cartesian DOA vector~(ACCDOA) representation as a single target for both the SED and SEL tasks. To efficiently estimate sound event locations and activities, we further propose RD3Net, which incorporates recurrent and convolution layers with dense skip connections and dilation. To generalize the models, we apply three data augmentation techniques: equalized mixture data augmentation~(EMDA), rotation of first-order Ambisonic~(FOA) singals, and multichannel extension of SpecAugment. Our systems demonstrate a significant improvement over the baseline system.

Naoya Takahashi, Mayank Kumar Singh, Sakya Basak et al.

Despite recent advances in voice separation methods, many challenges remain in realistic scenarios such as noisy recording and the limits of available data. In this work, we propose to explicitly incorporate the phonetic and linguistic nature of speech by taking a transfer learning approach using an end-to-end automatic speech recognition (E2EASR) system. The voice separation is conditioned on deep features extracted from E2EASR to cover the long-term dependence of phonetic aspects. Experimental results on speech separation and enhancement task on the AVSpeech dataset show that the proposed method significantly improves the signal-to-distortion ratio over the baseline model and even outperforms an audio visual model, that utilizes visual information of lip movements.

Naoya Takahashi, Sudarsanam Parthasaarathy, Nabarun Goswami et al.

In this paper we propose a method of single-channel speaker-independent multi-speaker speech separation for an unknown number of speakers. As opposed to previous works, in which the number of speakers is assumed to be known in advance and speech separation models are specific for the number of speakers, our proposed method can be applied to cases with different numbers of speakers using a single model by recursively separating a speaker. To make the separation model recursively applicable, we propose one-and-rest permutation invariant training (OR-PIT). Evaluation on WSJ0-2mix and WSJ0-3mix datasets show that our proposed method achieves state-of-the-art results for two- and three-speaker mixtures with a single model. Moreover, the same model can separate four-speaker mixture, which was never seen during the training. We further propose the detection of the number of speakers in a mixture during recursive separation and show that this approach can more accurately estimate the number of speakers than detection in advance by using a deep neural network based classifier.

Naoya Takahashi, Nabarun Goswami, Yuki Mitsufuji

Deep neural networks have become an indispensable technique for audio source separation (ASS). It was recently reported that a variant of CNN architecture called MMDenseNet was successfully employed to solve the ASS problem of estimating source amplitudes, and state-of-the-art results were obtained for DSD100 dataset. To further enhance MMDenseNet, here we propose a novel architecture that integrates long short-term memory (LSTM) in multiple scales with skip connections to efficiently model long-term structures within an audio context. The experimental results show that the proposed method outperforms MMDenseNet, LSTM and a blend of the two networks. The number of parameters and processing time of the proposed model are significantly less than those for simple blending. Furthermore, the proposed method yields better results than those obtained using ideal binary masks for a singing voice separation task.

Naoya Takahashi, Yuki Mitsufuji

This paper deals with the problem of audio source separation. To handle the complex and ill-posed nature of the problems of audio source separation, the current state-of-the-art approaches employ deep neural networks to obtain instrumental spectra from a mixture. In this study, we propose a novel network architecture that extends the recently developed densely connected convolutional network (DenseNet), which has shown excellent results on image classification tasks. To deal with the specific problem of audio source separation, an up-sampling layer, block skip connection and band-dedicated dense blocks are incorporated on top of DenseNet. The proposed approach takes advantage of long contextual information and outperforms state-of-the-art results on SiSEC 2016 competition by a large margin in terms of signal-to-distortion ratio. Moreover, the proposed architecture requires significantly fewer parameters and considerably less training time compared with other methods.

Naoya Takahashi, Michael Gygli, Luc Van Gool

We propose a new deep network for audio event recognition, called AENet. In contrast to speech, sounds coming from audio events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due to the lack of clear sub-word units that are present in speech. In order to incorporate this long-time frequency structure of audio events, we introduce a convolutional neural network (CNN) operating on a large temporal input. In contrast to previous works this allows us to train an audio event detection system end-to-end. The combination of our network architecture and a novel data augmentation outperforms previous methods for audio event detection by 16%. Furthermore, we perform transfer learning and show that our model learnt generic audio features, similar to the way CNNs learn generic features on vision tasks. In video analysis, combining visual features and traditional audio features such as MFCC typically only leads to marginal improvements. Instead, combining visual features with our AENet features, which can be computed efficiently on a GPU, leads to significant performance improvements on action recognition and video highlight detection. In video highlight detection, our audio features improve the performance by more than 8% over visual features alone.

Naoya Takahashi, Mitsuharu Matsumoto, Shuji Hashimoto

It is often required to extract the sound of an objective instrument played in concert with other instruments. Microphone array is one of the effective ways to enhance a sound from a specific direction. However it is not effective in an echoic room such as concert hall. The pickup microphone attached on the specific musical instrument is often employed to obtain the sound exclusively from other instrumental sounds. The obtained timbre differ from the one we hear at the usual listening position. The purpose of this paper is to propose a new method of sound separation that utilizes the piezoelectric device attached on the body of the instrument. The signal from the attached device has a different spectrum from the sound heard by the audience but has the same frequency components as the instrumental sound. Our idea is to use the device signal as a modifier of the sound focusing filter applied to the microphone sound at the listening position. The proposed method firstly estimates the frequency components of the signal from the piezoelectric device. The frequency characteristics for filtering the microphone sound are changed so that it pass the estimated frequency components. Thus we can extractthe target sound without distortion. The proposed method is a sort of dynamic sparseness approach. It was found that SNR is improved by 8.7dB through the experiments.

Naoya Takahashi, Tofigh Naghibi, Beat Pfister

Phonemic or phonetic sub-word units are the most commonly used atomic elements to represent speech signals in modern ASRs. However they are not the optimal choice due to several reasons such as: large amount of effort required to handcraft a pronunciation dictionary, pronunciation variations, human mistakes and under-resourced dialects and languages. Here, we propose a data-driven pronunciation estimation and acoustic modeling method which only takes the orthographic transcription to jointly estimate a set of sub-word units and a reliable dictionary. Experimental results show that the proposed method which is based on semi-supervised training of a deep neural network largely outperforms phoneme based continuous speech recognition on the TIMIT dataset.

Naoya Takahashi, Michael Gygli, Beat Pfister et al.

We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due to the lack of a clear sub-word unit. In order to incorporate the long-time frequency structure for AED, we introduce a convolutional neural network (CNN) with a large input field. In contrast to previous works, this enables to train audio event detection end-to-end. Our architecture is inspired by the success of VGGNet and uses small, 3x3 convolutions, but more depth than previous methods in AED. In order to prevent over-fitting and to take full advantage of the modeling capabilities of our network, we further propose a novel data augmentation method to introduce data variation. Experimental results show that our CNN significantly outperforms state of the art methods including Bag of Audio Words (BoAW) and classical CNNs, achieving a 16% absolute improvement.