Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recommendation

Incorporating multi-modal features as side information has recently become a trend in recommender systems. To elucidate user-item preferences, recent studies focus on fusing modalities via concatenation, element-wise sum, or attention mechanisms. Despite having notable success, existing approaches do not account for the modality-specific noise encapsulated within each modality. As a result, direct fusion of modalities will lead to the amplification of cross-modality noise. Moreover, the variation of noise that is unique within each modality results in noise alleviation and fusion being more challenging. In this work, we propose a new Spectrum-based Modality Representation (SMORE) fusion graph recommender that aims to capture both uni-modal and fusion preferences while simultaneously suppressing modality noise. Specifically, SMORE projects the multi-modal features into the frequency domain and leverages the spectral space for fusion. To reduce dynamic contamination that is unique to each modality, we introduce a filter to attenuate and suppress the modality noise adaptively while capturing the universal modality patterns effectively. Furthermore, we explore the item latent structures by designing a new multi-modal graph learning module to capture associative semantic correlations and universal fusion patterns among similar items. Finally, we formulate a new modality-aware preference module, which infuses behavioral features and balances the uni- and multi-modal features for precise preference modeling. This empowers SMORE with the ability to infer both user modality-specific and fusion preferences more accurately. Experiments on three real-world datasets show the efficacy of our proposed model. The source code for this work has been made publicly available at https://github.com/kennethorq/SMORE.

Aligning Speech to Languages to Enhance Code-switching Speech Recognition

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose the language alignment loss that performs frame-level language identification using pseudo language labels learned from the ASR decoder. This eliminates the need for frame-level language annotations. To further tackle the complex token alternatives for language modeling in bilingual scenarios, we propose to employ large language models via a generative error correction method. A linguistic hint that incorporates language information (derived from the proposed language alignment loss and decoded hypotheses) is introduced to guide the prompting of large language models. The proposed methods are evaluated on the SEAME dataset and data from the ASRU 2019 Mandarin-English code-switching speech recognition challenge. The incorporation of the proposed language alignment loss demonstrates a higher CS-ASR performance with only a negligible increase in the number of parameters on both datasets compared to the baseline model. This work also highlights the efficacy of language alignment loss in balancing primary-language-dominant bilingual data during training, with an 8.6% relative improvement on the ASRU dataset compared to the baseline model. Performance evaluation using large language models reveals the advantage of the linguistic hint by achieving 14.1% and 5.5% relative improvement on test sets of the ASRU and SEAME datasets, respectively.

Enhancing Code-switching Speech Recognition with Interactive Language Biases

Languages usually switch within a multilingual speech signal, especially in a bilingual society. This phenomenon is referred to as code-switching (CS), making automatic speech recognition (ASR) challenging under a multilingual scenario. We propose to improve CS-ASR by biasing the hybrid CTC/attention ASR model with multi-level language information comprising frame- and token-level language posteriors. The interaction between various resolutions of language biases is subsequently explored in this work. We conducted experiments on datasets from the ASRU 2019 code-switching challenge. Compared to the baseline, the proposed interactive language biases (ILB) method achieves higher performance and ablation studies highlight the effects of different language biases and their interactions. In addition, the results presented indicate that language bias implicitly enhances internal language modeling, leading to performance degradation after employing an external language model.

MERLIon CCS Challenge Evaluation Plan

This paper introduces the inaugural Multilingual Everyday Recordings- Language Identification on Code-Switched Child-Directed Speech (MERLIon CCS) Challenge, focused on developing robust language identification and language diarization systems that are reliable for non-standard, accented, spontaneous code-switched, child-directed speech collected via Zoom. Aligning closely with Interspeech 2023 theme, the main objectives of this inaugural challenge are to present a unique first-of-its-kind Zoom videocall dataset featuring English-Mandarin spontaneous code-switched child-directed speech, benchmark the current and novel language identification and language diarization systems in a code-switching scenario including extremely short utterances, and test the robustness of such systems under accented speech. The MERLIon CCS challenge features two task: language identification (Task 1) and language diarization (Task 2). Two tracks, open and closed, are available for each task, differing by the volume of data systems can be trained on. This paper describes the dataset, dataset annotation protocol, challenge tasks, open and closed tracks, evaluation metrics, and evaluation protocol.

Investigating model performance in language identification: beyond simple error statistics

Language development experts need tools that can automatically identify languages from fluent, conversational speech, and provide reliable estimates of usage rates at the level of an individual recording. However, language identification systems are typically evaluated on metrics such as equal error rate and balanced accuracy, applied at the level of an entire speech corpus. These overview metrics do not provide information about model performance at the level of individual speakers, recordings, or units of speech with different linguistic characteristics. Overview statistics may therefore mask systematic errors in model performance for some subsets of the data, and consequently, have worse performance on data derived from some subsets of human speakers, creating a kind of algorithmic bias. In the current paper, we investigate how well a number of language identification systems perform on individual recordings and speech units with different linguistic properties in the MERLIon CCS Challenge. The Challenge dataset features accented English-Mandarin code-switched child-directed speech.

MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization

To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns. We present the MERLIon CCS challenge, featuring a first-of-its-kind Zoom video call dataset of parent-child shared book reading, of over 30 hours with over 300 recordings, annotated by multilingual transcribers using a high-fidelity linguistic transcription protocol. The audio corpus features spontaneous and in-the-wild English-Mandarin code-switching, child-directed speech in non-standard accents with diverse language-mixing patterns recorded in a variety of home environments. This report describes the corpus, as well as LID and LD results for our baseline and several systems submitted to the MERLIon CCS challenge using the corpus.

Improving performance of real-time full-band blind packet-loss concealment with predictive network

Packet loss concealment (PLC) is a tool for enhancing speech degradation caused by poor network conditions or underflow/overflow in audio processing pipelines. We propose a real-time recurrent method that leverages previous outputs to mitigate artefact of lost packets without the prior knowledge of loss mask. The proposed full-band recurrent network (FRN) model operates at 48 kHz, which is suitable for high-quality telecommunication applications. Experiment results highlight the superiority of FRN over an offline non-causal baseline and a top performer in a recent PLC challenge.

Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improving CS-ASR from two perspectives: incorporating and disentangling language information. We incorporate language information in the CS-ASR model by dynamically biasing the model with token-level language posteriors which are outputs of a sequence-to-sequence auxiliary language diarization module. In contrast, the disentangling process reduces the difference between languages via adversarial training so as to normalize two languages. We conduct the experiments on the SEAME dataset. Compared to the baseline model, both the joint optimization with LD and the language posterior bias achieve performance improvement. The comparison of the proposed methods indicates that incorporating language information is more effective than disentangling for reducing language confusion in CS speech.

PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification

We propose a novel model to hierarchically incorporate phoneme and phonotactic information for language identification (LID) without requiring phoneme annotations for training. In this model, named PHO-LID, a self-supervised phoneme segmentation task and a LID task share a convolutional neural network (CNN) module, which encodes both language identity and sequential phonemic information in the input speech to generate an intermediate sequence of phonotactic embeddings. These embeddings are then fed into transformer encoder layers for utterance-level LID. We call this architecture CNN-Trans. We evaluate it on AP17-OLR data and the MLS14 set of NIST LRE 2017, and show that the PHO-LID model with multi-task optimization exhibits the highest LID performance among all models, achieving over 40% relative improvement in terms of average cost on AP17-OLR data compared to a CNN-Trans model optimized only for LID. The visualized confusion matrices imply that our proposed method achieves higher performance on languages of the same cluster in NIST LRE 2017 data than the CNN-Trans model. A comparison between predicted phoneme boundaries and corresponding audio spectrograms illustrates the leveraging of phoneme information for LID.

Enhance Language Identification using Dual-mode Model with Knowledge Distillation

In this paper, we propose to employ a dual-mode framework on the x-vector self-attention (XSA-LID) model with knowledge distillation (KD) to enhance its language identification (LID) performance for both long and short utterances. The dual-mode XSA-LID model is trained by jointly optimizing both the full and short modes with their respective inputs being the full-length speech and its short clip extracted by a specific Boolean mask, and KD is applied to further boost the performance on short utterances. In addition, we investigate the impact of clip-wise linguistic variability and lexical integrity for LID by analyzing the variation of LID performance in terms of the lengths and positions of the mimicked speech clips. We evaluated our approach on the MLS14 data from the NIST 2017 LRE. With the 3~s random-location Boolean mask, our proposed method achieved 19.23%, 21.52% and 8.37% relative improvement in average cost compared with the XSA-LID model on 3s, 10s, and 30s speech, respectively.