Abstract: Devices, systems, and methods for automatic real-time moderation of meetings, by a computerized or automated moderation unit able to manage, steer and guide the meeting in real-time and able to selectively generate and convey real-time differential notifications and advice to particular participants. A Meeting Moderator Bot monitors audio conversations in a meeting, and analyzes their textual equivalent; detects topics that were skipped or that should be discussed, and notifies participants; detects double-talk or interferences and generates warnings accordingly; detects absence of participants that are relevant to particular topics; detects that the conversation should shift to another topic on the agenda; generates other meeting steering notifications; and monitors compliance of the meeting participants with such steering notifications.

Abstract: Devices, systems, and methods of Capturing the Moment in audio discussions and recordings. A user utilizes an electronic device to record audio, or to participate in an audio conversation or an audio/video conversation. During the conversation, the user clicks on presses a button to create an audio bookmark at desired time-points. Later, the system generates separate a short audio-clip for a few sentences that were spoken before and after each such audio bookmarks. The system further generates an aggregated clip or summary of the bookmarked segments, as well as textual transcription of the bookmarked content.

Abstract: Devices, systems, and methods of Capturing the Moment in audio discussions and recordings. A user utilizes an electronic device to record audio, or to participate in an audio conversation or an audio/video conversation. During the conversation, the user clicks on presses a button to create an audio bookmark at desired time-points. Later, the system generates separate a short audio-clip for a few sentences that were spoken before and after each such audio bookmarks. The system further generates an aggregated clip or summary of the bookmarked segments, as well as textual transcription of the bookmarked content.

Abstract: Devices, systems, and methods of generating and utilizing visual representations for audio meetings. A method includes: receiving an audio recording of a meeting having multiple participants; determining, for each meeting participant, time-slots in which that meeting participant spoke during the meeting; generating and displaying an audio playback progress bar which visually differentiates among time-slots of different meeting participants. Hovering or selection of a particular time-point on the audio progress bar, causes generation and display of a textual phrase that was uttered at that time-point by a meeting participant, together with an indication of the speaker; and optionally with several other preceding phrases and following phrases. Transcript portions are also color-coded or visually-coded, to efficiently distinguish among phrases of various meeting participants.

Abstract: Devices, systems, and methods of generating and utilizing visual representations for audio meetings. A method includes: receiving an audio recording of a meeting having multiple participants; determining, for each meeting participant, time-slots in which that meeting participant spoke during the meeting; generating and displaying an audio playback progress bar which visually differentiates among time-slots of different meeting participants. Hovering or selection of a particular time-point on the audio progress bar, causes generation and display of a textual phrase that was uttered at that time-point by a meeting participant, together with an indication of the speaker; and optionally with several other preceding phrases and following phrases. Transcript portions are also color-coded or visually-coded, to efficiently distinguish among phrases of various meeting participants.

Abstract: Devices, systems, and methods of generating and playing navigatable podcasts. A method includes: receiving an audio recording of a podcast; performing automatic speech recognition of the audio recording of the podcast, to generate a textual transcript of the podcast; detecting vocal cues in the textual transcript of the podcast, wherein each detected vocal cue indicates a beginning of a new in-podcast topic of the podcast; automatically generating for the podcast a table of content having a list of in-podcast topics. An end-user device then displays the table of content of the podcast during its playback, and enables to skip or navigate among the displayed in-podcast topics.

Abstract: Devices, systems, and methods for assigning differential weight to participants in a meeting, and for automatically generating summaries of meetings. A transcript of the meeting is generated or obtained; and meeting data and meta-data is analyzed, optionally utilizing textual analysis and Natural Language Processing (NLP). Roles or titles are determined for each participant; and a differential weight is allocated to utterances of each participant based on his role or title. Optionally, the weight is modified based on the relation between the participant's role and the topic of an utterance, or by taking into account the level of activity or passiveness of each participant. Optionally, a high-ranking participant is assigned a prevailing weight, with regard to all topics or with regard to a subset of topics. The system generates automatically a summary of approved decisions, approved action items, rejected proposals, or other insights.

Abstract: Devices, systems, and methods for automatic real-time moderation of meetings, by a computerized or automated moderation unit able to manage, steer and guide the meeting in real-time and able to selectively generate and convey real-time differential notifications and advice to particular participants. A Meeting Moderator Bot monitors audio conversations in a meeting, and analyzes their textual equivalent; detects topics that were skipped or that should be discussed, and notifies participants; detects double-talk or interferences and generates warnings accordingly; detects absence of participants that are relevant to particular topics; detects that the conversation should shift to another topic on the agenda; generates other meeting steering notifications; and monitors compliance of the meeting participants with such steering notifications.

Abstract: Devices, systems, and methods for assigning differential weight to participants in a meeting, and for automatically generating summaries of meetings. A transcript of the meeting is generated or obtained; and meeting data and meta-data is analyzed, optionally utilizing textual analysis and Natural Language Processing (NLP). Roles or titles are determined for each participant; and a differential weight is allocated to utterances of each participant based on his role or title. Optionally, the weight is modified based on the relation between the participant's role and the topic of an utterance, or by taking into account the level of activity or passiveness of each participant. Optionally, a high-ranking participant is assigned a prevailing weight, with regard to all topics or with regard to a subset of topics. The system generates automatically a summary of approved decisions, approved action items, rejected proposals, or other insights.

Abstract: Noise in a speech-plus-noise input signal is suppressed by splitting the input signal into spectral channels and decreasing the gain in the each channel which has a low signal-to-noise ratio (SNR). A voice operated switch (VOX) acts to detect noise-only input to gate a background noise (input signal) estimator and also to gate a residual noise (output signal) estimator. The gain in each of the channels is controlled by the current value (a posteriori) input signal SNR estimate, modified by the prior value (a priori) input signal SNR estimate, and smoothed as a function of the residual (output noise signal) estimate.

Abstract: A voice operated switch employs digital signal processing techniques to examine audio signal frames having harmonic content to identify voiced phonemes and to determined whether the signal frame contains primarily speech or noise. The method and apparatus employ a multiple-stage, delayed-decision adaptive digital signal processing algorithm implemented through the use of commonly available electronic circuit components.