اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدQuery-graph with Cross-gating Attention Model for Text-to-Audio Grounding
69
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In this paper, we address the text-to-audio grounding issue, namely, grounding the segments of the sound event described by a natural language query in the untrimmed audio. This is a newly proposed but challenging audio-language task, since it requires to not only precisely localize all the on- and off-sets of the desired segments in the audio, but to perform comprehensive acoustic and linguistic understandings and reason the multimodal interactions between the audio and query. To tackle those problems, the existing method treats the query holistically as a single unit by a global query representation, which fails to highlight the keywords that contain rich semantics. Besides, this method has not fully exploited interactions between the query and audio. Moreover, since the audio and queries are arbitrary and variable in length, many meaningless parts of them are not filtered out in this method, which hinders the grounding of the desired segments. To this end, we propose a novel Query Graph with Cross-gating Attention (QGCA) model, which models the comprehensive relations between the words in query through a novel query graph. Besides, to capture the fine-grained interactions between audio and query, a cross-modal attention module that assigns higher weights to the keywords is introduced to generate the snippet-specific query representations. Finally, we also design a cross-gating module to emphasize the crucial parts as well as weaken the irrelevant ones in the audio and query. We extensively evaluate the proposed QGCA model on the public Audiogrounding dataset with significant improvements over several state-of-the-art methods. Moreover, further ablation study shows the consistent effectiveness of different modules in the proposed QGCA model.
قيم البحث
اقرأ أيضاً
Music creation is typically composed of two parts: composing the musical score, and then performing the score with instruments to make sounds. While recent work has made much progress in automatic music generation in the symbolic domain, few attempts
have been made to build an AI model that can render realistic music audio from musical scores. Directly synthesizing audio with sound sample libraries often leads to mechanical and deadpan results, since musical scores do not contain performance-level information, such as subtle changes in timing and dynamics. Moreover, while the task may sound like a text-to-speech synthesis problem, there are fundamental differences since music audio has rich polyphonic sounds. To build such an AI performer, we propose in this paper a deep convolutional model that learns in an end-to-end manner the score-to-audio mapping between a symbolic representation of music called the piano rolls and an audio representation of music called the spectrograms. The model consists of two subnets: the ContourNet, which uses a U-Net structure to learn the correspondence between piano rolls and spectrograms and to give an initial result; and the TextureNet, which further uses a multi-band residual network to refine the result by adding the spectral texture of overtones and timbre. We train the model to generate music clips of the violin, cello, and flute, with a dataset of moderate size. We also present the result of a user study that shows our model achieves higher mean opinion score (MOS) in naturalness and emotional expressivity than a WaveNet-based model and two commercial sound libraries. We open our source code at https://github.com/bwang514/PerformanceNet
Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the input text
using a generic text-to-speech (TTS) engine and then transform the voice to the desired voice using voice conversion (VC). A major problem of this framework is that VC is a challenging problem which usually needs a moderate amount of parallel training data to work satisfactorily. In this paper, we propose a one-stage context-aware framework to generate natural and coherent target speech without any training data of the target speaker. In particular, we manage to perform accurate zero-shot duration prediction for the inserted text. The predicted duration is used to regulate both text embedding and speech embedding. Then, based on the aligned cross-modality input, we directly generate the mel-spectrogram of the edited speech with a transformer-based decoder. Subjective listening tests show that despite the lack of training data for the speaker, our method has achieved satisfactory results. It outperforms a recent zero-shot TTS engine by a large margin.
Automated Audio Captioning is a cross-modal task, generating natural language descriptions to summarize the audio clips sound events. However, grounding the actual sound events in the given audio based on its corresponding caption has not been invest
igated. This paper contributes an AudioGrounding dataset, which provides the correspondence between sound events and the captions provided in Audiocaps, along with the location (timestamps) of each present sound event. Based on such, we propose the text-to-audio grounding (TAG) task, which interactively considers the relationship between audio processing and language understanding. A baseline approach is provided, resulting in an event-F1 score of 28.3% and a Polyphonic Sound Detection Score (PSDS) score of 14.7%.
In this paper, we propose a lightweight music-generating model based on variational autoencoder (VAE) with structured attention. Generating music is different from generating text because the melodies with chords give listeners distinguished polyphon
ic feelings. In a piece of music, a chord consisting of multiple notes comes from either the mixture of multiple instruments or the combination of multiple keys of a single instrument. We focus our study on the latter. Our model captures not only the temporal relations along time but the structure relations between keys. Experimental results show that our model has a better performance than baseline MusicVAE in capturing notes in a chord. Besides, our method accords with music theory since it maintains the configuration of the circle of fifths, distinguishes major and minor keys from interval vectors, and manifests meaningful structures between music phrases.
Channel is one of the important criterions for digital audio quality. General-ly, stereo audio two channels can provide better perceptual quality than mono audio. To seek illegal commercial benefit, one might convert mono audio to stereo one with fak
e quality. Identifying of stereo faking audio is still a less-investigated audio forensic issue. In this paper, a stereo faking corpus is first present, which is created by Haas Effect technique. Then the effect of stereo faking on Mel Frequency Cepstral Coefficients (MFCC) is analyzed to find the difference between the real and faked stereo audio. Fi-nally, an effective algorithm for identifying stereo faking audio is proposed, in which 80-dimensional MFCC features and Support Vector Machine (SVM) classifier are adopted. The experimental results on three datasets with five different cut-off frequencies show that the proposed algorithm can ef-fectively detect stereo faking audio and achieve a good robustness.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
