Automatic music transcription is the process of converting an audio recording into a symbolic representation using musical notation. It has numerous applications in music information retrieval, computational musicology, and the creation of interactive systems. Even for expert musicians, transcribing polyphonic pieces of music is not a trivial task, and while the problem of automatic pitch estim...

Spectrally efficient multi-antenna wireless communications is a key challenge as service demands continue to increase. At the same time, powering up radio access networks increases CO2 footprint. Hence, for an efficient radio access design, we design a directional modulation precoder for M QAM modulation with M = 4, 8, 16, 32. First, extended detection regions are defined in these constellation...

あらまし 次世代の移動無線通信では高速パケットアクセス技術が求められている.アクセス技術としてマルチ キャリア CDMA (MC-CDMA)が注目されている.そして,高速パケット伝送技術として自動再送要求(ARQ)に誤り 訂正符号化を組み合わせた Hybrid ARQ(HARQ)が検討されている.最近,誤り訂正符号として比較的少ない復号演 算量で強力な誤り訂正能力を有するLDPC符号の研究が盛んに行われている.LDPC符号化マルチコードMC-CDMA の平均ビット誤り率(BER)特性は直交拡散コード間のコード間干渉(ICI)の影響により劣化してしまう.ICI を低減す る技術として周波数領域適応干渉キャンセラ(FDAIC)が提案されている.本論文では,LDPC 符号語内適応変調およ び FDAIC によるスループット向上について検討している.周波数選択性フェージング環境下でのスループ...

This article gives a presentation of the Automatic Gain Control algorithm used in WCDMA (3rd generation mobile networks). The focus is on how the controller bandwidth influences settling times and modulation distortion. This will be investigated through simulation for two different channel cases.

In this paper, we propose to use speech modulation features for robust nonnative accent detection. Modulation spectrum carries long term temporal information of speech and may discriminate accents of native and nonnative speakers. For each speech segment to be tested, we extract a 10 dimension feature vector from modulation spectrum and use it for model training and testing. The proposed modula...

In a non-cooperative communication environment, automatic modulation classification (AMC) is an essential technology for analyzing signals and classifying different kinds of signal before they are demodulated. Deep learning (DL)-based AMC has been proposed as efficient method achieving high performance. However, most current DL-AMC methods have limited generalization capabilities under varying ...

Recently, deep learning-based image classification and speech recognition approaches have made extensive use of attention mechanisms to achieve state-of-the-art recognition, which demonstrates the effectiveness mechanisms. Motivated by fact that frequency time information modulated radio signals are crucial for modulation this letter proposes a time-frequency mechanism convolutional neural netw...