Hannes Gamper

Yuanchao Li, Azalea Gui, Dimitra Emmanouilidou et al.

The complex nature of musical emotion introduces inherent bias in both recognition and generation, particularly when relying on a single audio encoder, emotion classifier, or evaluation metric. In this work, we conduct a study on Music Emotion Recognition (MER) and Emotional Music Generation (EMG), employing diverse audio encoders alongside Frechet Audio Distance (FAD), a reference-free evaluation metric. Our study begins with a benchmark evaluation of MER, highlighting the limitations of using a single audio encoder and the disparities observed across different measurements. We then propose assessing MER performance using FAD derived from multiple encoders to provide a more objective measure of musical emotion. Furthermore, we introduce an enhanced EMG approach designed to improve both the variability and prominence of generated musical emotion, thereby enhancing its realism. Additionally, we investigate the differences in realism between the emotions conveyed in real and synthetic music, comparing our EMG model against two baseline models. Experimental results underscore the issue of emotion bias in both MER and EMG and demonstrate the potential of using FAD and diverse audio encoders to evaluate musical emotion more objectively and effectively.

Haleh Akrami, Hannes Gamper

Perceptual speech quality is an important performance metric for teleconferencing applications. The mean opinion score (MOS) is standardized for the perceptual evaluation of speech quality and is obtained by asking listeners to rate the quality of a speech sample. Recently, there has been increasing research interest in developing models for estimating MOS blindly. Here we propose a multi-task framework to include additional labels and data in training to improve the performance of a blind MOS estimation model. Experimental results indicate that the proposed model can be trained to jointly estimate MOS, reverberation time (T60), and clarity (C50) by combining two disjoint data sets in training, one containing only MOS labels and the other containing only T60 and C50 labels. Furthermore, we use a semi-supervised framework to combine two MOS data sets in training, one containing only MOS labels (per ITU-T Recommendation P.808), and the other containing separate scores for speech signal, background noise, and overall quality (per ITU-T Recommendation P.835). Finally, we present preliminary results for addressing individual rater bias in the MOS labels.

Ross Cutler, Ando Saabas, Tanel Parnamaa et al.

The ICASSP 2022 Acoustic Echo Cancellation Challenge is intended to stimulate research in acoustic echo cancellation (AEC), which is an important area of speech enhancement and still a top issue in audio communication. This is the third AEC challenge and it is enhanced by including mobile scenarios, adding speech recognition rate in the challenge goal metrics, and making the default sample rate 48 kHz. In this challenge, we open source two large datasets to train AEC models under both single talk and double talk scenarios. These datasets consist of recordings from more than 10,000 real audio devices and human speakers in real environments, as well as a synthetic dataset. We also open source an online subjective test framework and provide an online objective metric service for researchers to quickly test their results. The winners of this challenge are selected based on the average Mean Opinion Score achieved across all different single talk and double talk scenarios, and the speech recognition word acceptance rate.

Harishchandra Dubey, Vishak Gopal, Ross Cutler et al.

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. This is the 4th DNS challenge, with the previous editions held at INTERSPEECH 2020, ICASSP 2021, and INTERSPEECH 2021. We open-source datasets and test sets for researchers to train their deep noise suppression models, as well as a subjective evaluation framework based on ITU-T P.835 to rate and rank-order the challenge entries. We provide access to DNSMOS P.835 and word accuracy (WAcc) APIs to challenge participants to help with iterative model improvements. In this challenge, we introduced the following changes: (i) Included mobile device scenarios in the blind test set; (ii) Included a personalized noise suppression track with baseline; (iii) Added WAcc as an objective metric; (iv) Included DNSMOS P.835; (v) Made the training datasets and test sets fullband (48 kHz). We use an average of WAcc and subjective scores P.835 SIG, BAK, and OVRL to get the final score for ranking the DNS models. We believe that as a research community, we still have a long way to go in achieving excellent speech quality in challenging noisy real-world scenarios.

Chandan K A Reddy, Harishchandra Dubey, Kazuhito Koishida et al.

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. We recently organized a DNS challenge special session at INTERSPEECH and ICASSP 2020. We open-sourced training and test datasets for the wideband scenario. We also open-sourced a subjective evaluation framework based on ITU-T standard P.808, which was also used to evaluate participants of the challenge. Many researchers from academia and industry made significant contributions to push the field forward, yet even the best noise suppressor was far from achieving superior speech quality in challenging scenarios. In this version of the challenge organized at INTERSPEECH 2021, we are expanding both our training and test datasets to accommodate full band scenarios. The two tracks in this challenge will focus on real-time denoising for (i) wide band, and(ii) full band scenarios. We are also making available a reliable non-intrusive objective speech quality metric called DNSMOS for the participants to use during their development phase.

Kusha Sridhar, Ross Cutler, Ando Saabas et al.

The ICASSP 2021 Acoustic Echo Cancellation Challenge is intended to stimulate research in the area of acoustic echo cancellation (AEC), which is an important part of speech enhancement and still a top issue in audio communication and conferencing systems. Many recent AEC studies report good performance on synthetic datasets where the train and test samples come from the same underlying distribution. However, the AEC performance often degrades significantly on real recordings. Also, most of the conventional objective metrics such as echo return loss enhancement (ERLE) and perceptual evaluation of speech quality (PESQ) do not correlate well with subjective speech quality tests in the presence of background noise and reverberation found in realistic environments. In this challenge, we open source two large datasets to train AEC models under both single talk and double talk scenarios. These datasets consist of recordings from more than 2,500 real audio devices and human speakers in real environments, as well as a synthetic dataset. We open source two large test sets, and we open source an online subjective test framework for researchers to quickly test their results. The winners of this challenge will be selected based on the average Mean Opinion Score (MOS) achieved across all different single talk and double talk scenarios.

Ruihan Yang, Hannes Gamper, Sebastian Braun

We introduce a multi-modal diffusion model tailored for the bi-directional conditional generation of video and audio. We propose a joint contrastive training loss to improve the synchronization between visual and auditory occurrences. We present experiments on two datasets to evaluate the efficacy of our proposed model. The assessment of generation quality and alignment performance is carried out from various angles, encompassing both objective and subjective metrics. Our findings demonstrate that the proposed model outperforms the baseline in terms of quality and generation speed through introduction of our novel cross-modal easy fusion architectural block. Furthermore, the incorporation of the contrastive loss results in improvements in audio-visual alignment, particularly in the high-correlation video-to-audio generation task.

Ali Vosoughi, Dimitra Emmanouilidou, Hannes Gamper

Integrating audio and visual data for training multimodal foundational models remains a challenge. The Audio-Video Vector Alignment (AVVA) framework addresses this by considering AV scene alignment beyond mere temporal synchronization, and leveraging Large Language Models (LLMs) for data curation. AVVA implements a scoring mechanism for selecting aligned training data segments. It integrates Whisper, a speech-based foundation model, for audio and DINOv2 for video analysis in a dual-encoder structure with contrastive learning on AV pairs. Evaluations on AudioCaps, VALOR, and VGGSound demonstrate the effectiveness of the proposed model architecture and data curation approach. AVVA achieves a significant improvement in top-k accuracies for video-to-audio retrieval on all datasets compared to DenseAV, while using only 192 hrs of curated training data. Furthermore, an ablation study indicates that the data curation process effectively trades data quality for data quantity, yielding increases in top-k retrieval accuracies on AudioCaps, VALOR, and VGGSound, compared to training on the full spectrum of uncurated data.

Shivam Mehta, Nebojsa Jojic, Hannes Gamper

Integrating audio comprehension and generation into large language models (LLMs) remains challenging due to the continuous nature of audio and the resulting high sampling rates. Here, we introduce a novel approach that combines Variational Quantization with Conditional Flow Matching to convert audio into ultra-low bitrate discrete tokens of 0.23kpbs, allowing for seamless integration with text tokens in LLMs. We fine-tuned a pretrained text-based LLM using Low-Rank Adaptation (LoRA) to assess its effectiveness in achieving true multimodal capabilities, i.e., audio comprehension and generation. Our tokenizer outperforms a traditional VQ-VAE across various datasets with diverse acoustic events. Despite the substantial loss of fine-grained details through audio tokenization, our multimodal LLM trained with discrete tokens achieves competitive results in audio comprehension with state-of-the-art methods, though audio generation is poor. Our results highlight the need for larger, more diverse datasets and improved evaluation metrics to advance multimodal LLM performance.

Xilin Jiang, Hannes Gamper, Sebastian Braun

Acoustic scene perception involves describing the type of sounds, their timing, their direction and distance, as well as their loudness and reverberation. While audio language models excel in sound recognition, single-channel input fundamentally limits spatial understanding. This work presents Sci-Phi, a spatial audio large language model with dual spatial and spectral encoders that estimates a complete parameter set for all sound sources and the surrounding environment. Learning from over 4,000 hours of synthetic first-order Ambisonics recordings including metadata, Sci-Phi enumerates and describes up to four directional sound sources in one pass, alongside non-directional background sounds and room characteristics. We evaluate the model with a permutation-invariant protocol and 15 metrics covering content, location, timing, loudness, and reverberation, and analyze its robustness across source counts, signal-to-noise ratios, reverberation levels, and challenging mixtures of acoustically, spatially, or temporally similar sources. Notably, Sci-Phi generalizes to real room impulse responses with only minor performance degradation. Overall, this work establishes the first audio LLM capable of full spatial-scene description, with strong potential for real-world deployment. Demo: https://sci-phi-audio.github.io/demo

Sebastian Braun, Hannes Gamper

Deep learning based speech enhancement has made rapid development towards improving quality, while models are becoming more compact and usable for real-time on-the-edge inference. However, the speech quality scales directly with the model size, and small models are often still unable to achieve sufficient quality. Furthermore, the introduced speech distortion and artifacts greatly harm speech quality and intelligibility, and often significantly degrade automatic speech recognition (ASR) rates. In this work, we shed light on the success of the spectral complex compressed mean squared error (MSE) loss, and how its magnitude and phase-aware terms are related to the speech distortion vs. noise reduction trade off. We further investigate integrating pre-trained reference-less predictors for mean opinion score (MOS) and word error rate (WER), and pre-trained embeddings on ASR and sound event detection. Our analyses reveal that none of the pre-trained networks added significant performance over the strong spectral loss.

Sebastian Braun, Hannes Gamper, Chandan K. A. Reddy et al.

With recent research advancements, deep learning models are becoming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models can achieve outstanding results in terms of speech quality and background noise reduction, the main challenge is to obtain compact enough models, which are resource efficient during inference time. An important but often neglected aspect for data-driven methods is that results can be only convincing when tested on real-world data and evaluated with useful metrics. In this work, we investigate reasonably small recurrent and convolutional-recurrent network architectures for speech enhancement, trained on a large dataset considering also reverberation. We show interesting tradeoffs between computational complexity and the achievable speech quality, measured on real recordings using a highly accurate MOS estimator. It is shown that the achievable speech quality is a function of network complexity, and show which models have better tradeoffs.

Hannes Gamper, Dimitra Emmanouilidou, Sebastian Braun et al.

Reverberation negatively impacts the performance of automatic speech recognition (ASR). Prior work on quantifying the effect of reverberation has shown that clarity (C50), a parameter that can be estimated from the acoustic impulse response, is correlated with ASR performance. In this paper we propose predicting ASR performance in terms of the word error rate (WER) directly from acoustic parameters via a polynomial, sigmoidal, or neural network fit, as well as blindly from reverberant speech samples using a convolutional neural network (CNN). We carry out experiments on two state-of-the-art ASR models and a large set of acoustic impulse responses (AIRs). The results confirm C50 and C80 to be highly correlated with WER, allowing WER to be predicted with the proposed fitting approaches. The proposed non-intrusive CNN model outperforms C50-based WER prediction, indicating that WER can be estimated blindly, i.e., directly from the reverberant speech samples without knowledge of the acoustic parameters.

Ziqi Fan, Vibhav Vineet, Hannes Gamper et al.

Diffracted scattering and occlusion are important acoustic effects in interactive auralization and noise control applications, typically requiring expensive numerical simulation. We propose training a convolutional neural network to map from a convex scatterer's cross-section to a 2D slice of the resulting spatial loudness distribution. We show that employing a full-resolution residual network for the resulting image-to-image regression problem yields spatially detailed loudness fields with a root-mean-squared error of less than 1 dB, at over 100x speedup compared to full wave simulation.

Anderson R. Avila, Hannes Gamper, Chandan Reddy et al.

Estimating the perceived quality of an audio signal is critical for many multimedia and audio processing systems. Providers strive to offer optimal and reliable services in order to increase the user quality of experience (QoE). In this work, we present an investigation of the applicability of neural networks for non-intrusive audio quality assessment. We propose three neural network-based approaches for mean opinion score (MOS) estimation. We compare our results to three instrumental measures: the perceptual evaluation of speech quality (PESQ), the ITU-T Recommendation P.563, and the speech-to-reverberation energy ratio. Our evaluation uses a speech dataset contaminated with convolutive and additive noise, labeled using a crowd-based QoE evaluation, evaluated with Pearson correlation with MOS labels, and mean-squared-error of the estimated MOS. Our proposed approaches outperform the aforementioned instrumental measures, with a fully connected deep neural network using Mel-frequency features providing the best correlation (0.87) and the lowest mean squared error (0.15)